LLM/AI Model Engineer – Training, Evaluation & Benchmarking at QubeLabs Systems Private Limited · Delhi · 3 - 5 years · ₹10L - ₹20L / yr · Posted 9 Oct 2026
LLM/AI Model Engineer – Training, Evaluation & Benchmarking
Python
Deep LearningLLM/AI Model Engineer – Training, Evaluation & Benchmarking
Location: New Delhi, India (On-site)
Employment Type: Full-time
Experience: 3–5 years
Industry: Enterprise AI / Generative AI / Machine Learning / NLP
About QubeLabs
QubeLabs is building the next generation of Enterprise AI Systems that transform workforce operations and intelligence for the financial services industry.
Our platform combines Conversational AI, Agentic AI, workflow automation, proprietary language models and enterprise intelligence. Our flagship product, QubeLabs Workmate, serves banks, NBFCs, MFIs, wealth management firms, insurance companies and fintechs across India and Europe.
At the core of our AI platform is the Vectro Series, our proprietary family of language models designed for enterprise and financial-services use cases.
We are looking for an LLM/AI Model Engineer to build the training pipelines, datasets and evaluation infrastructure required to continuously improve the Vectro Series.
Role Overview
You will work closely with the Head of AI, Research Partners and engineering teams to implement and operationalize LLM training approaches and build a reliable model improvement lifecycle:
Data Preparation → Training → Evaluation → Benchmarking → Error Analysis → Model Improvement
The role combines hands-on LLM fine-tuning, dataset engineering, tokenization, evaluation framework development and model quality management.
Key Responsibilities
1. LLM Training & Fine-tuning
Build and maintain pipelines for training and fine-tuning open-source foundation models for the Vectro Series.
Implement supervised fine-tuning (SFT), parameter-efficient fine-tuning (PEFT), LoRA/QLoRA and domain adaptation techniques; support continued pre-training where required.
Manage training configurations, checkpoints, model versions and experiment tracking.
Optimize training workflows for computational efficiency, reproducibility and reliability.
Translate model development approaches defined with the Head of AI and Research Partners into practical, scalable training pipelines.
2. Training Data & Tokenization
Build data pipelines to collect, clean, filter, normalize, deduplicate and validate training data.
Develop instruction-tuning, SFT and domain-specific datasets for financial-services and enterprise use cases.
Implement tokenization workflows, tokenizer configuration, vocabulary management, sequence packing, truncation and padding.
Address data representation challenges involving financial terminology, numerical values and multilingual content.
Maintain dataset versioning, lineage and quality controls, incorporating identified data gaps and relevant model failures into future training data.
3. Golden Dataset & Model Evaluation
Build and maintain QubeLabs' Golden Dataset to evaluate key model capabilities and target use cases.
Develop automated evaluation pipelines and reusable evaluation harnesses, combining automated metrics with human assessment where appropriate.
Evaluate accuracy, reasoning, factuality, instruction following, safety, multilingual performance and financial-domain capabilities.
Establish consistent evaluation methodology and regression tests to measure changes across model versions.
4. Benchmarking & Error Analysis
Evaluate Vectro against relevant public benchmarks and proprietary QubeLabs BFSI/enterprise benchmarks.
Compare results with relevant open-source and commercial models using consistent evaluation conditions.
Analyze failures, identify root causes across data, training and model behavior, and translate findings into actionable improvements.
Maintain reproducible benchmark results and reports to track model strengths, limitations and progress.
5. Model Quality & Release
Define model release quality gates and ensure each major release meets agreed evaluation and benchmark criteria.
Support red-teaming, robustness and safety testing.
Coordinate with the Head of AI, Research Partners and engineering teams to ensure validated model improvements are suitable for integration into production systems.
Experience
3–5 years in Machine Learning, Deep Learning, NLP, Generative AI or related fields.
Hands-on experience training or fine-tuning LLMs using open-source foundation models.
Practical experience building training pipelines, preparing datasets and evaluating model performance.
Experience with GPU-based training; distributed training is an advantage.
Financial-services, multilingual AI or enterprise AI experience is preferred.
Required Skills
LLM & Machine Learning: Large Language Models, Transformer architectures, Generative AI, NLP, Deep Learning, SFT, PEFT, LoRA/QLoRA, fine-tuning and continued pre-training.
Frameworks & Infrastructure: Python, PyTorch, Hugging Face Transformers, Hugging Face Tokenizers, GPU computing, experiment tracking and ML pipelines.
Data & Tokenization: Tokenization, tokenizer configuration, text preprocessing, sequence packing, dataset construction, data quality, versioning and lineage.
Evaluation & Benchmarking: Golden datasets, LLM evaluation, evaluation harnesses, automated and human evaluation, LLM-as-a-Judge, public and domain-specific benchmarks, regression testing and error analysis.
The role requires the ability to build both the model training pipeline and the measurement system that determines whether the model has actually improved.
What Success Looks Like
Reliable and reproducible training and fine-tuning pipelines for the Vectro Series.
High-quality training datasets, tokenization workflows and a comprehensive Golden Dataset.
Automated evaluation and benchmarking infrastructure with measurable model quality gates.
Clear, reproducible evidence of model performance against public, proprietary BFSI and relevant competing-model benchmarks.
A continuous improvement loop that converts evaluation findings into measurable gains across successive Vectro releases.
Key Performance Indicators
Training pipeline reliability and experiment throughput.
Training data quality and coverage.
Golden Dataset and evaluation coverage.
Benchmark reproducibility and model performance improvement.
Accuracy of error diagnosis and effectiveness of regression detection.
Time required to complete training, evaluation and benchmarking cycles.
Compliance with model release quality criteria.
Why Join QubeLabs?
Build the proprietary Vectro Series of enterprise and financial-services language models.
Develop model training, evaluation and benchmarking infrastructure from the ground up.
Work closely with the Head of AI and Research Partners.
Solve real-world AI challenges across financial services.
Develop proprietary datasets, benchmarks and model improvement systems.
Contribute directly to production AI systems serving customers across India and Europe.
Preferred Candidate Profile
B.Tech, M.Tech, MS or PhD in Computer Science, AI, ML, Mathematics or a related field.
3–5 years of relevant experience with strong practical skills in Python, PyTorch, LLM fine-tuning and training data pipelines.
Working knowledge of tokenization, evaluation datasets, benchmarking and regression testing.
Experience with open-source models such as Llama, Qwen, Mistral or similar is preferred.
Ability to independently build reliable model training and evaluation systems from scratch.
QubeLabs is an equal opportunity employer and values diversity and inclusion. We encourage applications from qualified candidates regardless of background or identity.
Shubham Vishwakarma
Full Stack Developer - Averlon
About QubeLabs Systems Private Limited
About
Company social profiles
Similar jobs (10)
Machine Learning (ML)PythonThis is a remote position.
About Leegality:
Leegality works with large Indian businesses to digitally transform critical compliance processes in a fast, easy and secure way.
We have multiple products across 2 categories:
Document Infrastructure:
Products that help businesses build paperless processes at scale:
- Document Execution Workflow: A unified platform for businesses to digitally execute (eSign, eStamp, Template Pre-fill, Document Fraud Prevention etc.) agreements, forms and other documents in a compliant way. Currently in use by 2000+ Indian businesses from giants like HDFC and SBI Cards to high-growth disruptors like goDigit and Cars24.
- Contract Management: An AI-powered platform for businesses to quickly review, negotiate and take action on contract
- Signstation: A simple platform for businesses to digitally sign simple documents like invoices, policies and letters in a cost effective manner
Consent Infrastructure:
- Consentin: An end-to-end DPDP and Privacy compliance platform for Indian businesses
- Consentin Lens: A data discovery platform for businesses to identify the personal data they collect and store.
If you’re interested in building mission critical software that operates at population scale (75 million + Indians have signed at least one document through Leegality) then join Leegality.
Curious about our impact? Explore our customer success stories: leegality.com/case-studies
Our Culture
At Leegality, trust, ownership, transparency, and having fun while doing meaningful work are core to how we operate — not just values on paper. Our team rated us an incredible 97 eNPS for FY 2023–24 — the highest among 175+ startups surveyed.
We focus deeply on helping our people grow and stay motivated. Some of the perks you’ll enjoy:
- Flexible working hours
- Hybrid work setup
- Bi-annual performance appraisals
- A culture that rewards initiative, curiosity, and impact
If you're looking for a place where you can make a real difference while working with smart, driven, and genuinely nice people, welcome to Leegality.
Location: Hybrid
Job Brief:
- As a Machine Learning Engineer specializing in Computer Vision (CV) and Natural Language Processing (NLP), you will develop solutions to interesting technical problems, exploring exciting growth opportunities and having a real impact on our product, particularly focusing on document and content intelligence.
- To ensure success, you should demonstrate solid data science knowledge and experience in a related ML, CV, or NLP role. A first-class engineer will be someone whose expertise enhances our systems for document intelligence and content processing
Responsibilities:
- Designing machine learning systems, self-running artificial intelligence (AI) software, and specialized models for Computer Vision and Natural Language Processing applications.
- Transforming data science prototypes and applying appropriate deep learning algorithms and tools to text and image/document data.
- Solving complex CV and NLP problems with multi-layered data types, such as image/document classification, information extraction, semantic search, and object detection.
- Optimizing existing machine learning models, with a focus on high-performance model deployment for CV and NLP tasks.
- Developing ML algorithms (including large language models/LLMs and computer vision models) to analyze huge volumes of historical text, image, and document data to make predictions and automate workflows.
- Running tests, performing statistical analysis, and interpreting test results for CV/NLP model performance.
- Documenting machine learning processes, model architectures, and data pipelines.
- Keeping abreast of developments in machine learning, Computer Vision, and Natural Language Processing.
Requirements:
- 3+ years of relevant experience in Machine Learning Engineering, with a strong focus on Computer Vision and/or Natural Language Processing.
- Advanced proficiency with Python.
- Extensive knowledge of ML frameworks, libraries (e.g., PyTorch, Transformers), data structures, data modeling, and software architecture.
- Experience with building and maintaining scalable RESTful APIs (e.g., FastAPI).
- In-depth knowledge of mathematics, statistics, deep learning (CNNs, RNNs, Transformers), and algorithms.
- Superb analytical and problem-solving abilities, especially for unstructured data challenges.
- Great communication and collaboration skills.
- Excellent time management and organizational abilities.
- Experience with cloud platforms (e.g., AWS) for model deployment and MLOps.
Recruitment Process:
- Our hiring process combines AI-powered evaluations with structured interviews to ensure a fair and seamless experience.
- You will be contacted via email with the next steps upon being shortlisted.
- The process may include Assessments, AI-enabled interviews, and In-Person Interviews with our team.
- Final selection and CTC will be based on your overall performance and experience.
Apply directly through our career page: https://careers.leegality.com/jobs/Careers
For more information about us please visit our:
Our Company and Culture: https://bit.ly/3Iqm5SB
Our Website: www.leegality.com/
Our LinkedIn Page: www.linkedin.com/company/leegality/
Leegality's Privacy Notice: https://www.leegality.com/employee-privacy-notice
PythonWe are looking for an AI Evaluation Engineer to evaluate, test, and improve the quality, reliability, and performance of large language models (LLMs) and generative AI applications.
You will design evaluation datasets, develop automated testing pipelines, analyze model outputs, and build metrics and tools to measure AI system performance across real-world use cases.
The ideal candidate has strong Python programming skills, an analytical mindset, and an interest in LLM evaluation, AI training, and data-driven model improvement.
Key Responsibilities
- Design, develop, and maintain evaluation datasets and test cases for LLMs and AI-powered applications.
- Evaluate model outputs for factual accuracy, relevance, reasoning, instruction following, consistency, and safety.
Required Qualifications
- 2+ years of experience in software development, data science, machine learning, or a related technical field.
- Strong proficiency in Python and experience with data-processing libraries such as pandas and NumPy.
Strong Senior AI Engineer Profile with production-grade LLM and Python expertise
2
Mandatory (Experience 1): Must have at least 3+ years of professional AI/ML engineering experience with demonstrated track record of delivering production-grade AI systems in real-world environments
3
Mandatory (Tech skill 1): Must have strong programming skills in Python and SQL, with hands-on ML/data libraries (scikit-learn, pandas, numpy) and deep-learning frameworks (PyTorch or TensorFlow), plus REST API design
4
Mandatory (Experience 2): Must have hands-on experience building and deploying production-grade ML/LLMs including RAG pipelines, document parsing, information extraction, and text processing on large-scale unstructured data (preprocessing, chunking, embeddings, feature engineering)
5
Mandatory (Tech skill 2): Must have strong NLP / extraction-focused ML depth — transformers, embeddings, vector databases, RAG, LLM integrations, and agentic workflows.
6
Mandatory (Tech skill 3): Must have hands-on experience with AWS (SageMaker, Bedrock, EC2, Lambda) and Azure (AI Foundry, Azure OpenAI) for model training, fine-tuning, deployment, and inference at scale
7
Mandatory (Tech skill 4): Must have experience with multi-agentic frameworks / orchestration tools (Claude Code, LangGraph, LangChain, CrewAI)
8
Mandatory (Tech skill 5): Must have hands-on experience with MLOps ecosystem including experiment tracking (MLflow, Weights & Biases), model versioning/registry, automated retraining, and CI/CD (GitHub Actions, Azure DevOps, Docker, Kubernetes)
9
Mandatory (Tech skill 6): Must have experience with evaluation frameworks (precision, recall, F1, field-level accuracy) and iterative model improvement, plus AI observability (Prometheus, Grafana, SLOs).
10
Mandatory (Team Leadership): Must have experience leading projects or teams, managing technical deliverables, and mentoring, with strong problem-solving in ambiguous challenges
11
Mandatory (Education) - B.Tech or B.E. If graduated in BCA or BCS, they should have a Maters or Post graduation
12
Mandatory (Company): B2B Tech/Consulting/B2B Software
Strong AI Engineer / Machine Learning Engineer profiles.
2
Mandatory (Experience 1) – Must have minimum 3+ years of hands-on experience in Data Science, Machine Learning, Applied AI, NLP, Deep Learning, or Generative AI solutions.
3
Mandatory (Experience 2) – Must have strong hands-on experience in Python programming, SQL, data analysis, feature engineering, model development, and production-grade ML applications.
4
Mandatory (Experience 3) – Must have experience working with Machine Learning and Deep Learning frameworks such as PyTorch, TensorFlow, Keras, Scikit-learn, or equivalent.
5
Mandatory (Experience 4) – Must have hands-on experience working on NLP, embeddings, semantic search, text classification, document understanding, recommendation systems, or similar AI/ML use cases.
6
Mandatory (Experience 5) – Must have experience working with Large Language Models (LLMs) such as GPT, Llama, Mistral, Claude, Gemini, Phi, or similar foundation models.
7
Mandatory (Experience 6) – Must have hands-on experience building or implementing RAG (Retrieval Augmented Generation) systems, vector search, knowledge retrieval, embeddings, chunking, indexing, or semantic retrieval solutions.
8
Mandatory (Experience 7) – Must have experience working with Git, CI/CD practices, production environments, and scalable AI/ML systems.
Mandatory ( Pedigree) - B.TECH / M.TECH from Tier 1 Colleges (IIT's, NIT's, BITS) are Considered.
PythonEGNYTE YOUR CAREER. SPARK YOUR PASSION.
Egnyte is a place where we spark opportunities for amazing people. We believe that every role has meaning, and every Egnyter should be respected. With 23,000 customers worldwide and growing, you can make an impact by protecting their valuable data. When joining Egnyte, you’re not just landing a new career; you become part of a team of Egnyters who are doers, thinkers, and collaborators who embrace and live by our values:
Invested Relationships
Fiscal Prudence
Candid Conversations
ABOUT EGNYTE
Egnyte is the secure multi-cloud platform for content security and governance that enables organizations to better protect and collaborate on their most valuable content. Established in 2008, Egnyte has democratized cloud content security for more than 23,000 organizations, helping customers improve data security, maintain compliance, prevent and detect ransomware threats, and boost employee productivity on any app, any cloud, anywhere.
WHAT YOU’LL DO:
- Fine-tune and train SLMs using Hugging Face, TRL, and adapter methods (LoRA, QLoRA, PEFT)
- Optimize models for inference via quantization, pruning, and knowledge distillation
- Deploy models to edge devices, mobile, and local servers with strict latency targets
- Build end-to-end MLOps pipelines from data ingestion to deployment
- Monitor model accuracy, latency, and hardware utilization in production
- Evaluate model quality using benchmarking frameworks and custom evaluation suites
YOUR QUALIFICATIONS:
- SLM Development & Fine-tuning: Train and fine-tune SLMs using Hugging Face and Knowledge on Adaptors.
- Model Optimization: Apply quantization, pruning, knowledge distillation, and optimization for lightweight, efficient models.
- Edge Deployment: Deploy models to edge devices, mobile, and local servers, etc.
- Pipeline Engineering: Build end-to-end MLOps pipelines — from data ingestion to deployment.
- Performance Monitoring: Track model accuracy, latency, and CPU/GPU usage in production.
Good to have
- Deployment experience on edge or mobile environments
- Knowledge of ONNX export and cross-platform inference
- MLOps tooling — experiment tracking, model registries, CI/CD for ML
EQUAL EMPLOYMENT OPPORTUNITY
At Egnyte, we celebrate our unique differences and thrive on our diversity for our employees, our products, our customers, our investors, and our communities. Our global Egnyte Employee Communities (EECs) support representation and inclusion across our diverse workplace. Egnyters are encouraged to bring their whole selves to work and to appreciate the many differences that collectively make Egnyte a higher-performing company and a great place to be.
Egnyte will not allow any form of retaliation against employees who raise issues of equal employment opportunity. To ensure the workplace is free of artificial barriers, violation of this policy including any improper retaliatory conduct will lead to discipline, up to and including discharge. All employees must cooperate with all investigations conducted pursuant to this policy.
Strong Senior AI Engineer Profile with production-grade LLM and Python expertise
2
Mandatory (Experience 1): Must have at least 3+ years of professional AI/ML engineering experience with demonstrated track record of delivering production-grade AI systems in real-world environments
3
Mandatory (Tech skill 1): Must have strong programming skills in Python and SQL, with hands-on ML/data libraries (scikit-learn, pandas, numpy) and deep-learning frameworks (PyTorch or TensorFlow), plus REST API design
4
Mandatory (Experience 2): Must have hands-on experience building and deploying production-grade ML/LLMs including RAG pipelines, document parsing, information extraction, and text processing on large-scale unstructured data (preprocessing, chunking, embeddings, feature engineering)
5
Mandatory (Tech skill 2): Must have strong NLP / extraction-focused ML depth — transformers, embeddings, vector databases, RAG, LLM integrations, and agentic workflows.
6
Mandatory (Tech skill 3): Must have hands-on experience with AWS (SageMaker, Bedrock, EC2, Lambda) and Azure (AI Foundry, Azure OpenAI) for model training, fine-tuning, deployment, and inference at scale
7
Mandatory (Tech skill 4): Must have experience with multi-agentic frameworks / orchestration tools (Claude Code, LangGraph, LangChain, CrewAI)
8
Mandatory (Tech skill 5): Must have hands-on experience with MLOps ecosystem including experiment tracking (MLflow, Weights & Biases), model versioning/registry, automated retraining, and CI/CD (GitHub Actions, Azure DevOps, Docker, Kubernetes)
9
Mandatory (Tech skill 6): Must have experience with evaluation frameworks (precision, recall, F1, field-level accuracy) and iterative model improvement, plus AI observability (Prometheus, Grafana, SLOs).
10
Mandatory (Team Leadership): Must have experience leading projects or teams, managing technical deliverables, and mentoring, with strong problem-solving in ambiguous challenges
11
Mandatory (Education) - B.Tech or B.E. If graduated in BCA or BCS, they should have a Maters or Post graduation
12
Mandatory (Company): B2B Tech/Consulting/B2B Software
Kody Technolab Limited is seeking an experienced AI/ML Engineer to design, develop, and deploy cutting-edge Artificial Intelligence and Machine Learning solutions. The ideal candidate will have
strong expertise in Machine Learning, Deep Learning, Generative AI, LLMs, MLOps, and cloud-based AI deployments.
Key Responsibilities
• Design, develop, and deploy Machine Learning and Deep Learning models for classification, regression, recommendation systems, NLP, Computer Vision, and Generative AI applications.
• Build and maintain end-to-end ML pipelines including data preprocessing, feature engineering, model training, validation, evaluation, and deployment.
• Develop AI solutions using PyTorch, TensorFlow, Scikit-learn, Hugging Face, and related frameworks.
• Work with Large Language Models (LLMs) and foundation models such as GPT, BERT, Llama, Claude, and Stable Diffusion.
• Collaborate with product, engineering, and business teams to translate requirements into scalable AI solutions.
• Optimize model performance, scalability, and reliability for production environments.
• Implement MLOps best practices using tools such as MLflow, Docker, Kubernetes, and Kubeflow.
• Stay updated with emerging trends and research in AI, ML, Deep Learning, and Generative AI.
Required Qualifications
• Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, Mathematics, or a related field.
• 7+ years of hands-on experience in AI/ML product development.
• Strong proficiency in Python and ML frameworks including Scikit-learn, TensorFlow, PyTorch, and Hugging Face.
• Experience with Generative AI, LLMs, GANs, VAEs, diffusion models, and prompt engineering.
• Strong understanding of the ML lifecycle including model training, tuning, deployment, monitoring, and optimization.
• Experience with MLOps tools such as MLflow, Docker, Kubeflow, and CI/CD pipelines.
• Experience with AWS, Azure, or GCP cloud platforms.
• Strong problem-solving and analytical skills.
Preferred Skills
• Fine-tuning and deployment of Large Language Models.
• Experience with RAG (Retrieval Augmented Generation) architectures.
• Contributions to open-source AI projects or research publications.
• Knowledge of model interpretability, data annotation, and feature engineering.
• C++ experience for high-performance AI applications.
Why Join Kody Technolab Limited?
Opportunity to work on innovative AI products, Generative AI solutions, robotics integrations,
and enterprise-scale applications while collaborating with a highly skilled technology team.
Visit the Website to know more about us.
Company Website - Kody Technolab | Deep Tech Company in Robotics & AI Solution
Kody Robots | Robotics Company in India for Autonomous Robots
About the role
We are seeking an AI Engineer to build and implement AI systems for content production at scale. You'll work at the intersection of engineering and content designing prompt pipelines, integrating generative models, and building the tooling that turns source material into finished creative output. The ideal candidate is technically strong but also has taste: someone who understands story and craft, and can tell the difference between output that's technically correct and output that's actually good.
Responsibilities
- Build and iterate on prompt pipelines and multi-agent workflow components
- Design and integrate agentic workflows orchestrate multi-step, tool-using agents that plan, call models, and hand off between stages in production
- Deploy and serve open-source models set up inference endpoints, manage GPU compute, and optimize for latency and cost
- Write evals compare outputs against references, quantify quality, and feed results back into the pipeline
- Work on data pipelines: structured extraction from messy source text, localization, similarity/dedup
- Debug and maintain pipeline stages in production
What you bring:
- (1+/3+) years of engineering experience, or a strong portfolio of shipped projects
- Solid Python fundamentals clean, working, readable code
- Hands-on experience with LLM APIs and prompt engineering (personal projects count)
- Comfort with Git, REST APIs, and working in a Linux environment
- A feel for content and narrative you can judge whether generated output is actually good, not just valid
- Curiosity and clear communication you ask good questions and don't stay stuck silently
Preferred
- Exposure to agent/orchestration frameworks (LangGraph, LangChain, CrewAI)
- Familiarity with vector databases, embeddings, or RAG (Qdrant, pgvector)
- Hands-on work with open-source generative media models Flux, LTX, Wan, or similar
- Experience deploying open-source models for inference (vLLM, ComfyUI, Replicate/Cog, Docker + GPU)
- Experience writing evals or LLM-as-judge scoring
- Node.js and Fastapi familiarity, or experience deploying on AWS
About the role
We are seeking an AI Engineer to build and implement AI systems for content production at scale. You'll work at the intersection of engineering and content designing prompt pipelines, integrating generative models, and building the tooling that turns source material into finished creative output. The ideal candidate is technically strong but also has taste: someone who understands story and craft, and can tell the difference between output that's technically correct and output that's actually good.
Responsibilities
- Build and iterate on prompt pipelines and multi-agent workflow components
- Design and integrate agentic workflows orchestrate multi-step, tool-using agents that plan, call models, and hand off between stages in production
- Deploy and serve open-source models set up inference endpoints, manage GPU compute, and optimize for latency and cost
- Write evals compare outputs against references, quantify quality, and feed results back into the pipeline
- Work on data pipelines: structured extraction from messy source text, localization, similarity/dedup
- Debug and maintain pipeline stages in production
What you bring:
- (1+/3+) years of engineering experience, or a strong portfolio of shipped projects
- Solid Python fundamentals clean, working, readable code
- Hands-on experience with LLM APIs and prompt engineering (personal projects count)
- Comfort with Git, REST APIs, and working in a Linux environment
- A feel for content and narrative you can judge whether generated output is actually good, not just valid
- Curiosity and clear communication you ask good questions and don't stay stuck silently
Preferred
- Exposure to agent/orchestration frameworks (LangGraph, LangChain, CrewAI)
- Familiarity with vector databases, embeddings, or RAG (Qdrant, pgvector)
- Hands-on work with open-source generative media models Flux, LTX, Wan, or similar
- Experience deploying open-source models for inference (vLLM, ComfyUI, Replicate/Cog, Docker + GPU)
- Experience writing evals or LLM-as-judge scoring
- Node.js and Fastapi familiarity, or experience deploying on AWS
PythonLocation -Bangalore
Work Mode -Fully in-office, 6 days a week
Experience -3+ years in AI engineering, with LLM-based systems shipped to production
About the Role
● The AI Engineer will own systems that read, search and reason over project and tender documents.
● Inputs include large tender packages, scanned PDFs, BOQs, tables, forms and engineering drawings such as P&IDs.; Outputs should include accurate answers with source references, structured data and workflows used by estimators and project teams in live bids, planning, procurement and execution.
● The role covers taking features from initial experiments to production and owning their accuracy, latency and cost after release.
Key Responsibilities
Agents and Retrieval
● Build AI agents that plan and execute multi-step tasks using document search, tools and APIs.
● Build RAG pipelines covering ingestion, retrieval, reranking and answers with source references.
● Use agent workflows within retrieval to refine searches, collect supporting evidence and verify outputs.
Document Intelligence
● Build extraction pipelines for PDFs, scanned documents, tables and forms.
● Convert unstructured tender content into structured data that the platform can use.
Vision and Image Understanding
● Build image-understanding workflows for P&IDs;, including symbols, equipment, labels and connections.
● Locate and remove selected elements from diagram images while preserving surrounding content.
Quality and Reliability
● Create evaluation datasets and automated checks to measure accuracy and catch regressions.
● Debug failures across retrieval, agent decisions, tool calls and model outputs.
Product and Production
● Build backend services and REST APIs. ● Integrate AI features into the Workwise web application.
● Take features from experiment to production while managing reliability, latency and cost
Required Qualifications
● 3+ years of hands-on experience building AI systems, including at least one LLM-based application running in production.
● Strong Python and software engineering fundamentals.
● Experience with backend services, REST APIs, databases, authentication and frontend integration.
● Experience building applications using LLM APIs.
● Working knowledge of RAG, embeddings, retrieval and vector databases.
● Experience with tool calling, structured outputs and multi-step agent workflows.
● Working understanding of multimodal models and image processing for visual analysis and editing.
● Systematic evaluation skills: measuring results and investigating system failures.
● Ownership of implementation, testing, deployment and ongoing improvement.
Good to Have
● OCR, document layout analysis or complex table extraction.
● Computer vision experience, including object detection, segmentation or image inpainting.
● Familiarity with construction, procurement or tender documents.
● Cloud infrastructure and production monitoring.
● Working knowledge of Go.
Follow CutshortShubham Vishwakarma
Full Stack Developer - Averlon