Senior Al Engineer

Senior AI Engineer

Code Generation, Agent Architecture & LLM Systems

📍 Mumbai (On-site) | Full-time | 5+ years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are hiring a Senior AI Engineer for a dedicated client engagement focused on building an AI-powered application builder platform - a product where users describe software in plain English and the system generates, previews, and iteratively refines working code.

The mandatory requirement for this role is hands-on production experience shipping LLM-powered systems with agent architectures, with experience in code generation or developer tooling contexts a strong advantage.

The role is product-focused and deeply hands-on. You will own everything between the user's prompt and correct code landing in the project: the agentic loop, code generation pipeline, context management, evaluation suite, and model cost strategy.

You will work alongside the Senior MLOps Engineer who operationalises the infrastructure around your system, and collaborate closely with backend, frontend, and DevOps engineers.

Responsibilities:

Agent Architecture

Design and own the agentic loop for the platform - request interpretation, planning, tool-calling sequence (read file, edit file, run build, search code, install package), and stop conditions.

Make and revisit architectural decisions on single-agent vs. multi-agent designs, including planner/executor splits and dedicated build-repair sub-agents.

Code Generation Pipeline

Own the end-to-end generation flow: task classification, context gathering, planning, targeted edits, verification, and commit.

Implement diff/search-replace-based file editing with fuzzy matching and fallback strategies.

Enforce scope discipline so the agent makes minimal diffs and does not modify code it was not asked to touch.

Self-Repair Loop

Build and tune the automated repair loop that pipes compiler, lint, build, and runtime errors back to the model with retry budgets and model escalation.

This loop is the primary quality lever - the difference between 60-70% and 90%+ build success rates.

Context Management

Build file-relevance retrieval so the agent sees the right files, not the whole codebase: dependency graphs, AST/tree-sitter-based chunking, embeddings, recency signals, and hybrid retrieval.

Implement conversation summarisation and memory for long sessions, and address long-project degradation through codebase summaries and periodic consistency passes.

Own token budgeting and prompt caching strategy.

Prompt Engineering as a Discipline

Own the system prompt and per-task prompt variants (new feature, bug fix, styling change).

Maintain few-shot examples and enforce coding conventions, stack rules, and prohibited behaviours such as no hardcoded secrets and no whole-file rewrites.

Version prompts like code with changelogs and rollback capability.

Evaluation and Quality Measurement

Design and own the evaluation suite: representative test prompts run on every prompt and model change, scored on build success rate, instruction adherence, and output quality including LLM-as-judge and visual/screenshot checks where relevant.

Define regression gates that block quality-degrading changes from shipping.

Treat evals the way engineers treat automated testing: versioned, automated, and tracked over time.

This responsibility is non-negotiable at this level.

Model Strategy and Cost

Design model routing - cheap and fast models for classification and small edits, frontier models for complex generation.

Drive cost optimisation through prompt caching, diff-based edits over full-file rewrites, and tighter context selection.

Track cost per agent run and tokens per task; evaluate new model releases against the eval suite and lead migrations when results justify it.

Safety and Reliability of Agent Behaviour

Defend against prompt injection from user content and fetched web content.

Ensure secrets never appear in generated client code.

Define what the agent's tools may and may not do in collaboration with the platform team.

Contribute to output moderation and abuse-pattern awareness.

Mentorship and Engineering Standards

Run code reviews, define engineering conventions for AI work, and raise the engineering bar across the AI team.

Work closely with the Senior MLOps Engineer on handoff of eval design, prompt configurations, and model routing logic.

Requirements:

Hands-on Production Ownership of LLM-Powered Systems with Agent Architectures (Mandatory)

Must have personally shipped and operated at least one complex production AI system - agentic, multi-step, or code generation - with end-to-end ownership of architecture, evaluation, and cost.

POCs, internal demos, and tutorial-grade work do not qualify.

5+ Years of Professional Software or AI Engineering Experience

With at least 3 years focused on LLM applications, AI engineering, or production AI systems.

Candidates with strong backend backgrounds and a clear, substantive pivot into LLM systems qualify.

Strong Python Proficiency and Service Development

Production-grade Python with FastAPI or equivalent: type hints, async patterns, streaming responses, testing, and packaging.

Not notebook-only.

Depth Across LLM APIs and Agent Systems

Production experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or open-weight models (vLLM, Ollama, Together).

Production experience with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.

Hands-on with tool calling, structured outputs, and multi-step reasoning.

Demonstrated, Systematic Evaluation Practice - Non-Negotiable

Must have built evaluation harnesses that gate production releases, not ad-hoc testing.

Hands-on with at least one of LangSmith, Langfuse, Promptfoo, Ragas, or DeepEval.

Candidates with no systematic answer to evaluation should not be considered at senior level regardless of other strengths.

Cost Discipline for Production AI

Track record of measurable cost optimisation on production AI features.

Able to speak in specifics: cost per request, savings achieved through caching or model routing, context reduction decisions.

AWS Working Knowledge

Hands-on with EC2, S3, IAM, and Docker.

Comfort with CI/CD workflows and deploying AI services.

Awareness of LLM Security Failure Modes

Familiar with prompt injection patterns, understands that system prompt rules alone are insufficient, and has experience with output validation and content safety in production.

Nice to Have

• Experience with AST/tree-sitter tooling, diff-based editing systems, or compiler-adjacent work
• MCP server authoring
• Open-source AI contributions
• Published technical writing on LLM systems
• Multi-modal model experience
• Fine-tuning exposure (LoRA, QLoRA, PEFT)

Role Overview 

We are looking for an AI Engineer to design, build, and ship production AI systems, including agentic AI applications, for enterprise clients. This is a hands-on engineering role: you will write production code, build and evaluate models and agents, and work closely with architects and product teams to take solutions from prototype to scale. 

Key Responsibilities 

Design and build agentic AI systems: agent workflows, tool/function-calling, memory, and human-in-the-loop patterns. Build and productionise RAG pipelines, prompt-based applications, and LLM integrations across providers. Develop and maintain data and ML pipelines: feature engineering, model training, evaluation, and monitoring. Integrate AI systems with enterprise applications (CRMs, ERPs, ITSM tools) via APIs, events, and MCP-based tool servers. Implement guardrails, prompt-injection defences, and evaluation frameworks to keep AI systems safe and reliable in production. 

Write clean, tested, production-grade code and participate actively in code and design reviews. 

Collaborate with architects, product managers, and delivery teams to translate requirements into working AI solutions. Troubleshoot and optimise AI systems for accuracy, latency, and cost in production. 

Required Qualifications 

8–12 years of hands-on software engineering experience, with a strong, unbroken technical track record. Hands-on experience building and shipping AI/ML systems in production, not just POCs. 

Practical experience with agentic AI systems and at least one major agent framework (LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Bedrock Agents/Strands, or Semantic Kernel). 

Experience with LLM/GenAI systems: RAG pipelines, prompt engineering, structured outputs, and tool calling across providers. 

Strong Python skills (TypeScript/Node.js a plus), with production-grade testing, CI/CD, and API design practices. Working knowledge of ML fundamentals: model evaluation, feature engineering, and experimentation. Cloud-native experience on AWS and/or Azure: containers, serverless, event backbones, and vector databases. Understanding of LLM safety and reliability practices: guardrails, prompt-injection defences, and observability. 

Job Description – AI Engineer (End-to-End Development & Deployment)

Role Summary

We are looking for an AI Engineer with hands-on experience in designing, developing, deploying, and maintaining Generative/Agentic AI solutions in production. The ideal candidate should have end-to-end ownership of AI applications, from development to deployment, monitoring, and optimization.

Key Responsibilities

●        Design, build, and deploy Generative/Agentic AI solutions.

●        Develop applications using LLMs, RAG, AI agents, and vector databases.

●        Build scalable APIs and integrate AI solutions with enterprise applications.

●        Implement CI/CD pipelines, containerization, and MLOps best practices.

●        Monitor, optimize, and maintain production AI systems.

●        Collaborate with cross-functional teams to deliver business-driven AI solutions.

Required Skills

●       Strong programming skills in Python.

●       Experience with vector databases (e.g., Pinecone, FAISS, ChromaDB) and graph memory systems

●       Knowledge of atleast one agent development framework: Google ADK (preferred), LangChain/LangGraph/LlamaIndex, CrewAI

●       Experience with LLMs, RAG, GenAI, AgenticAI Agents

●       Hands-on experience with FastAPI, and REST APIs.

●       Knowledge of Docker, Kubernetes, Git, CI/CD.

●       Experience with AWS, Azure, or GCP. 

●       Experience with security compliance, monitoring and observability tools such as AWS CloudWatch, Azure Monitor, Google Cloud Monitoring.

AI Engineer

LLMs, Agents & AI Services

📍 Mumbai (On-site) | Full-time | 2-4 years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

AI is core to how we design, deliver, and scale software for our customers.

We are hiring an AI Engineer for a dedicated client engagement building a complex production AI platform, working on the AI capabilities and agentic features at the core of the product.

The mandatory requirement for this role is at least one AI feature personally shipped to production for real users, with operational ownership.

The role suits someone who thinks quickly on solutioning, can take an ambiguous problem to a working prototype in days, and has the discipline to carry it through to production with predictable economics.

You will work alongside the Senior AI Engineer and the wider pod, with ownership of parts of the AI surface area of the product.

Responsibilities:

Solutioning and POCs

Translate ambiguous customer problems into working POCs at speed.

Pick the right model, framework, and architecture, and demonstrate value early before scaling investment.

LLM Application Development

Build AI features and services using LLM APIs from OpenAI, Anthropic, Google, and self-hosted open-weight models (Llama, Qwen, Mistral).

Choose the right model per use case based on cost, latency, capability, and context-window trade-offs.

Agentic System Design

Design and implement agentic workflows using LangGraph, CrewAI, AutoGen, LlamaIndex Agents, or custom orchestration.

Cover tool use, planning, memory, and multi-step reasoning appropriate to the problem.

API and Service Development

Build production AI services and APIs using Python and FastAPI.

Handle streaming responses, async processing, structured outputs, retries, and graceful degradation when models or tools fail.

Retrieval and Tool Integration

Implement RAG pipelines with vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma), embeddings, chunking strategies, hybrid search, and reranking.

Integrate external tools, internal APIs, and document sources through tool-calling and MCP-style patterns.

Cost Analysis and Unit Economics

Model the per-request and per-user cost of every AI feature before it ships.

Track token usage, prompt caching, batching, and model-routing strategies.

Drive measurable improvements in unit economics.

Production Hardening

Add observability and tracing (LangSmith, Langfuse, OpenTelemetry), guardrails, content safety checks, prompt injection defences, and fallback behaviour.

Prompt Engineering and Evaluation

Design, test, and iterate prompts with measured outcomes.

Build evaluation harnesses for accuracy, hallucination, latency, and cost.

Run benchmarks across models and prompt variants before locking in a design.

Requirements:

AI Feature Shipped to Production (Mandatory)

Must have personally built and shipped at least one AI feature that runs in production for real users, with operational ownership.

POCs, internal demos, and one-off scripts do not qualify.

2 to 4 Years of Professional Software or AI Engineering Experience

With at least one production AI feature owned end to end.

Strong Python Proficiency and API Development with FastAPI

Comfort with type hints, async, packaging, testing, streaming responses, and authentication.

Production-grade Python, not notebook-only code.

Hands-on Depth Across the LLM and Agent Stack

Working experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or self-hosted open-weight models (vLLM, Ollama, Together, Replicate).

Working familiarity with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.

Working knowledge of RAG, embeddings, and vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma).

Solutioning Speed and POC Velocity

Demonstrated ability to move from a fuzzy problem to a working prototype in days.

Strong instinct for what to build first, what to defer, and what to throw away.

Cost Discipline for Production AI

Ability to calculate, monitor, and optimise the cost of LLM APIs, tokens, embeddings, vector store usage, and infrastructure.

Treats unit economics as a first-class concern.

AWS Familiarity

Working knowledge of EC2, S3, IAM, and at least one of Bedrock, SageMaker, or equivalent.

Comfortable in a Fast-Moving Environment

Self-directed, comfortable with ambiguity, takes ownership without being asked, and ships under shifting priorities.

Strong Written and Spoken English Communication

Able to explain trade-offs to non-AI engineers, designers, product managers, and clients in plain language.

Nice to Have

• fine-tuning or LoRA, QLoRA, PEFT exposure
• MCP server authoring
• eval framework experience (LangSmith, Promptfoo, Ragas, DeepEval)
• open-source AI contributions
• multi-modal models (vision, audio)

Design and develop Agentic AI systems using LLMs, tools, memory,

workflows, and MCP.

Build production-grade RAG pipelines, including ingestion, chunking,

embeddings, retrieval, reranking, and evaluation.

Implement context engineering strategies for improving LLM accuracy,

relevance, and reliability.

Develop and integrate MCP-based tools and services for AI agents.

Work with LLMs, SLMs, quantized models, and model optimization

techniques for efficient inference.

Develop scalable backend services and APIs for AI applications.

Design databases and data models supporting AI/agentic applications.

Implement AI observability covering latency, token usage, cost, failures,

quality, and agent/tool execution.

Apply AI governance and responsible AI practices, including security,

access control, data privacy, and auditability.

Optimize AI systems for latency, scalability, cost, and reliability.

Collaborate with engineering and product teams to take AI solutions from

POC to production.

Strong hands-on experience with GenAI, LLMs, and Agentic AI.

Experience building RAG applications.

Strong understanding of Context Engineering and prompt/context

optimization.

Role Overview

We are looking for a hands-on AI/ML Engineer to design, develop, and deploy

production-ready GenAI and Agentic AI applications. The role involves building

intelligent agents, RAG pipelines, AI APIs, backend services, and scalable AI

infrastructure with a strong focus on context engineering, observability,

governance, and model optimisation.

Key Responsibilities

Required Skills

Practical experience with MCP (Model Context Protocol).

Experience with frameworks such as LangChain, LangGraph,

LlamaIndex, or equivalent.

Knowledge of LLM/SLM deployment and quantization techniques.

Strong Python backend development experience.

Experience developing REST APIs using FastAPI/Flask or equivalent.

Strong understanding of SQL/NoSQL databases and database design.

Experience with vector databases such as Qdrant, Pinecone, Weaviate,

ChromaDB, or FAISS.

Understanding of AI observability, evaluation, monitoring, and

governance.

Experience with cloud platforms and production deployment is preferred.

Strong understanding of software engineering principles, Git, testing, and

CI/CD.

About LeadSquared

LeadSquared is a leading sales execution and marketing automation platform trusted by 2,000+ businesses globally, including healthcare, education, financial services, and real estate. Headquartered in Bengaluru with offices across the US, UK, UAE, and Southeast Asia, we empower sales teams to close faster, smarter, and at scale.

Our AI team is at the forefront of integrating cutting-edge large language model capabilities into enterprise workflows — building intelligent agents, copilots, and automation systems that redefine how businesses operate.

Role Overview

We are looking for a Senior AI Engineer with hands-on experience building LLM-powered agents and agentic AI systems. You will design, develop, and deploy autonomous AI pipelines that solve complex, multi-step business problems — from lead qualification and follow-up automation to intelligent CRM workflows and beyond.

This role is ideal for someone who is deeply excited about the frontier of AI, can move fast, and wants their work to directly impact millions of sales professionals worldwide.

Key Responsibilities

•

Design and build LLM-powered agentic systems using frameworks such as LangChain, LlamaIndex, AutoGen, or CrewAI to automate complex, multi-step workflows.

•

Develop and maintain Retrieval-Augmented Generation (RAG) pipelines with vector databases (Pinecone, Weaviate, Chroma, pgvector) for domain-specific knowledge grounding.

•

Build and integrate tool-use and function-calling capabilities into AI agents, enabling dynamic interaction with internal APIs, databases, and third-party services.

•

Implement prompt engineering strategies including chain-of-thought, few-shot prompting, and structured output parsing to ensure reliable agent behavior.

•

Design evaluation frameworks and observability pipelines (LangSmith, Helicone, custom metrics) to monitor agent performance, accuracy, and cost.

•

Collaborate with product, sales, and domain teams to translate business requirements into AI-driven solutions and features.

•

Optimize LLM inference for latency and cost using techniques like caching, model distillation, quantization, and batching.

•

Stay current with the rapidly evolving LLM ecosystem and proactively propose improvements and new approaches.

•

Contribute to internal best practices, documentation, and knowledge-sharing across the engineering org.

Required Qualifications

Experience

•

2–4 years of professional software engineering experience, with at least 1–2 years focused on LLM/AI systems.

•

Proven experience shipping LLM-based products or agentic AI systems into production environments.

Technical Skills

•

Strong proficiency in Python and familiarity with async programming patterns for AI pipelines.

•

Hands-on experience with LLM APIs: OpenAI (GPT-4o), Anthropic (Claude), Google (Gemini), or open-source models (Llama, Mistral).

•

Experience with agentic frameworks: LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, or similar.

•

Solid understanding of RAG architectures, embedding models, and semantic search.

•

Experience with vector databases and similarity search infrastructure.

•

Knowledge of REST APIs, microservices architecture, and containerization (Docker/Kubernetes).

Problem-Solving & Mindset

•

Strong ability to decompose ambiguous, open-ended problems into structured AI system designs.

•

Experience with prompt debugging, LLM evaluation, and iterative refinement workflows.

•

Ability to balance research exploration with engineering pragmatism to ship reliable systems.

Preferred Qualifications

•

Experience with multi-agent orchestration and agent memory systems (short-term and long-term).

•

Familiarity with fine-tuning or RLHF workflows for domain adaptation.

•

Background in NLP, information retrieval, or conversational AI.

•

Prior experience in B2B SaaS or CRM domain is a plus.

•

Contributions to open-source AI/ML projects or published research/blogs.

•

Experience with cloud platforms: AWS, GCP, or Azure — particularly AI/ML services

Must of Skills/Experience 

• System Design

• Python

• TensorFlow

• Google ADK or Lang Graph

• Lang Chain , Lang Graph

• Spark

• Agentic AI Design

• ML Ops

• MCP (client and server)

• FastAPI

• Doc Factory

• RAG

• Golang

• LLMs – Gemini, Open AI

• NLP

• Dev Assistant - AI based code - generation

(Qwen or Claude or Copilot)

• CI/CD

• Good in oral and written communication,

collaboration and be a team player

Good to have skills 

• DevOps with K8

• Scripting

• Java

• REST API

• UV

• ReACT

• DocFactory

• Unix

Role Overview

We are looking for an experienced AI/ML Engineer with strong expertise in Python, Generative AI, LLMs, LangChain, and LangGraph. The candidate will be responsible for designing and developing AI-powered applications, intelligent agents, and scalable LLM-based solutions.

Key Responsibilities

• Design and develop AI/ML and Generative AI applications using Python and modern LLM technologies.
• Build LLM-based applications and AI agents using LangChain and LangGraph.
• Develop agentic workflows involving tool calling, memory, reasoning, and multi-step orchestration.
• Integrate LLMs such as OpenAI, Azure OpenAI, Anthropic, Gemini, or other foundation models.
• Develop RAG (Retrieval-Augmented Generation) pipelines using vector databases.
• Work with embeddings, prompt engineering, semantic search, and document processing.
• Develop scalable APIs and backend services using Python, FastAPI, or Flask.
• Build and integrate AI solutions with existing applications and enterprise systems.
• Deploy and maintain AI/ML solutions on cloud platforms.
• Collaborate with data scientists, software engineers, and product teams to develop business-focused AI solutions.

Required Skills

• Strong hands-on experience in Python programming.
• Strong experience in AI/ML and Generative AI.
• Hands-on experience with LLMs and LLM-based application development.
• Strong experience with LangChain and/or LangGraph.
• Experience building AI Agents / Agentic AI workflows.
• Strong understanding of RAG, embeddings, vector databases, and prompt engineering.
• Experience with vector databases such as FAISS, Pinecone, Chroma, Weaviate, or Azure AI Search.
• Experience developing REST APIs using FastAPI/Flask.
• Good understanding of Machine Learning, NLP, and deep learning concepts.
• Experience with Azure / AWS / GCP cloud platforms.

Good to Have

• Experience with multi-agent systems and agent orchestration.
• Knowledge of MLOps / LLMOps.
• Experience with Docker, Kubernetes, and CI/CD.
• Knowledge of LLM evaluation, monitoring, observability, and AI governance.
• Experience with Azure OpenAI, Azure AI Foundry, or AWS Bedrock.

We are building an advanced, AI-driven multi-agent software system designed to revolutionize task automation and code generation. This is a futuristic AI platform capable of:

✅ Real-time self-coding based on tasks  

✅ Autonomous multi-agent collaboration  

✅ AI-powered decision-making  

✅ Cross-platform compatibility (Desktop, Web, Mobile)  

We are hiring a highly skilled **AI Engineer & Full-Stack Developer** based in India, with a strong background in AI/ML, multi-agent architecture, and scalable, production-grade software development.

### Responsibilities:

- Build and maintain a multi-agent AI system (AutoGPT, BabyAGI, MetaGPT concepts)  

- Integrate large language models (GPT-4o, Claude, open-source LLMs)  

- Develop full-stack components (Backend: Python, FastAPI/Flask, Frontend: React/Next.js)  

- Work on real-time task execution pipelines  

- Build cross-platform apps using Electron or Flutter  

- Implement Redis, Vector databases, scalable APIs  

- Guide the architecture of autonomous, self-coding AI systems  

### Must-Have Skills:

- Python (advanced, AI applications)  

- AI/ML experience, including multi-agent orchestration  

- LLM integration knowledge  

- Full-stack development: React or Next.js  

- Redis, Vector Databases (e.g., Pinecone, FAISS)  

- Real-time applications (websockets, event-driven)  

- Cloud deployment (AWS, GCP)  

### Good to Have:

- Experience with code-generation AI models (Codex, GPT-4o coding abilities)  

- Microservices and secure system design  

- Knowledge of AI for workflow automation and productivity tools  

Join us to work on cutting-edge AI technology that builds the future of autonomous software.

About the role

We are building AI systems that read, understand and act on real business documents, bank statements, financial reports, policy documents and forms and putting them into production where accuracy and cost both matters.

This is not a research role and it is not a prompt-writing role. You will own features end to end: pick and deploy open-source models, build the pipelines around them, measure whether they actually work on our documents, drive the cost per document down, and keep the whole thing running in production.

You will work closely with the engineering and product teams, and your work will be directly used by business users from day one.

What you will do

Deploy and evaluate open-source models

• Select, deploy and benchmark open-source LLMs and vision-language models for specific, narrow use cases not general chat.
• Build evaluation sets from real documents and define what "good" means numerically (field-level accuracy, extraction recall, hallucination rate) before shipping.
• Run structured comparisons between models and approaches, and write up the trade-offs so the team can make a decision.
• Apply quantization, batching and other optimizations to fit models into a sensible GPU budget.

Build and optimize AI orchestration

• Design multi-step pipelines that combine deterministic code, ML models and LLM calls and know when not to use an LLM.
• Optimize for latency, cost and reliability: caching, batching, request routing, fallback tiers, retries and graceful degradation.
• Instrument pipelines so failures are visible and traceable rather than silent.

Ship to production

• Package models and services with Docker, expose them behind clean APIs, and deploy them to our GPU and CPU infrastructure.
• Handle the unglamorous production concerns: cold starts, timeouts, concurrency limits, versioning, rollback and monitoring.
• Own on-call-style responsibility for the AI features you build, including cost tracking.

Must-have skills

Programming & engineering

• Strong Python: type hints, async/await, dataclasses/Pydantic, clean module design, testing.
• REST API development with FastAPI (or Flask/Django with a willingness to move to FastAPI).
• Git, code review discipline, and the ability to write code someone else can maintain.
• Comfortable in Linux and on the command line.

Machine learning fundamentals

• Working knowledge of PyTorch and the Hugging Face ecosystem (transformers, tokenizers, accelerate).
• Understanding of inference-time concepts: tokenization, context windows, batching, precision (FP16/BF16/INT8), memory footprint.
• Ability to read a model card and a paper well enough to judge whether a model fits a use case.

Document processing

• Hands-on experience with at least two of: pypdfium2, PyMuPDF, pdfplumber, pdfminer.six, Docling, Unstructured, Surya, DocTR, LayoutLM family.
• Practical OCR experience (Tesseract, PaddleOCR, or a cloud OCR) and an understanding of when OCR is the wrong tool.
• Experience extracting tables from PDFs and dealing with merged cells, multi-line rows, and inconsistent column layouts.

Strongly preferred

You will be a much stronger candidate with any of these. We do not expect all of them.

Model serving & optimization

• vLLM, TGI, Ollama, llama.cpp, or Triton Inference Server.
• Quantization formats and tooling: GGUF, AWQ, GPTQ, bitsandbytes, ONNX Runtime, INT8 export.
• Serverless GPU platforms: Modal, RunPod, Replicate, Baseten including cold-start and container-lifecycle management.
• LoRA / QLoRA fine-tuning with PEFT for narrow, task-specific improvements.

Vision-language models

• Practical use of open VLMs: Qwen2.5-VL, InternVL, Granite Vision, Molmo, Phi-Vision, or similar.
• Awareness of where VLMs hallucinate especially on numeric and financial content and patterns for constraining them (using the model for layout only, sourcing values from the text layer, constrained decoding).

Orchestration & pipelines

• Workflow orchestration: Dagster, Airflow, Prefect, or Temporal.
• Async job patterns: Celery, RQ, or platform-native spawn/poll patterns.
• LLM orchestration frameworks (LangGraph, LlamaIndex, Haystack) with the judgement to know when plain Python is a better answer.
• Structured output enforcement: Instructor, Outlines, XGrammar, JSON schema / tool-use modes.

Evaluation & observability

• Building golden datasets and regression suites for extraction tasks.
• Eval tooling: promptfoo, DeepEval, Ragas, or in-house harnesses.
• LLM tracing and monitoring: Langfuse, Arize Phoenix, LangSmith, OpenTelemetry.

Nice extras

• Rule engines and policy evaluation (Open Policy Agent / Rego, Drools, rule-engine).
• Experience in fintech, lending, insurance or accounting documents.
• Handling of PII and data-security practices in document pipelines.
• Contributions to open-source ML or document-processing projects.

Why join us

• Real production ownership from month one your work goes to actual users, not a demo.
• Genuinely hard technical problems in document AI, not wrappers over an API.
• Small team, short decision cycles, direct access to leadership.
• Budget and freedom to evaluate and adopt new open-source models as they land.

To apply: send your CV along with a short note on one AI system you have taken to production what it did, what the accuracy was, and what broke.