Software Engineer - Python

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)

About NonStop io Technologies

NonStop io Technologies is a value-driven company with a strong focus on process-oriented software engineering. We specialize in Product Development and have a decade's worth of experience in building web and mobile applications across various domains. NonStop io Technologies follows core principles that guide its operations and believes in staying invested in a product's vision for the long term. We are a small but proud group of individuals who believe in the 'givers gain' philosophy and strive to provide value in order to seek value. We are committed to and specialize in building cutting-edge technology products and serving as trusted technology partners for startups and enterprises. We pride ourselves on fostering innovation, learning, and community engagement. Join us to work on impactful projects in a collaborative and vibrant environment.

Brief Description:

We're seeking an AI/ML Engineer to join our team. As AI/ML Engineer, you will be responsible for designing, developing, and implementing artificial intelligence (AI) and machine learning (ML) solutions to solve real-world business problems. You will work closely with engineering teams, including software engineers, domain experts, and product managers, to deploy and integrate Applied AI/ML solutions into the products that are being built at NonStop io. Your role will involve researching cutting-edge algorithms and data processing techniques, and implementing scalable solutions to drive innovation and improve the overall user experience.

Responsibilities

● Applied AI/ML engineering; Building engineering solutions on top of the AI/ML tooling available in the industry today. Eg: Engineering APIs around OpenAI

● AI/ML Model Development: Design, develop, and implement machine learning models and algorithms that address specific business challenges, such as natural language processing, computer vision, recommendation systems, anomaly detection, etc.

● Data Preprocessing and Feature Engineering: Cleanse, preprocess, and transform raw data into suitable formats for training and testing AI/ML models. Perform feature engineering to extract relevant features from the data

● Model Training and Evaluation: Train and validate AI/ML models using diverse datasets to achieve optimal performance. Employ appropriate evaluation metrics to assess model accuracy, precision, recall, and other relevant metrics

● Data Visualization: Create clear and insightful data visualizations to aid in understanding data patterns, model behaviour, and performance metrics

● Deployment and Integration: Collaborate with software engineers and DevOps teams to deploy AI/ML models into production environments and integrate them into various applications and systems

● Data Security and Privacy: Ensure compliance with data privacy regulations and implement security measures to protect sensitive information used in AI/ML processes

● Continuous Learning: Stay updated with the latest advancements in AI/ML research, tools, and technologies, and apply them to improve existing models and develop novel solutions

● Documentation: Maintain detailed documentation of the AI/ML development process, including code, models, algorithms, and methodologies for easy understanding and future reference.

Qualifications & Skills

● Bachelor's, Master's, or PhD in Computer Science, Data Science, Machine Learning, or a related field. Advanced degrees or certifications in AI/ML are a plus

● Proven experience as an AI/ML Engineer, Data Scientist, or related role, ideally with a strong portfolio of AI/ML projects

● Proficiency in programming languages commonly used for AI/ML. Preferably Python

● Familiarity with popular AI/ML libraries and frameworks, such as TensorFlow, PyTorch, scikit-learn, etc.

● Familiarity with popular AI/ML Models such as GPT3, GPT4, Llama2, BERT etc.

● Strong understanding of machine learning algorithms, statistics, and data structures

● Experience with data preprocessing, data wrangling, and feature engineering

● Knowledge of deep learning architectures, neural networks, and transfer learning

● Familiarity with cloud platforms and services (e.g., AWS, Azure, Google Cloud) for scalable AI/ML deployment

● Solid understanding of software engineering principles and best practices for writing maintainable and scalable code

● Excellent analytical and problem-solving skills, with the ability to think critically and propose innovative solutions

● Effective communication skills to collaborate with cross-functional teams and present complex technical concepts to non-technical stakeholders

Job Title : Python Django Developer

Experience : 3+ Years

Location : Gurgaon (Work from Office)

Job Summary :

We are looking for an experienced Python Django Developer with strong expertise in building scalable web applications and distributed systems. The ideal candidate must have hands-on experience with Django, Redis, Celery, RabbitMQ, PostgreSQL, and Kafka to design and optimize high-performance applications.

Mandatory Skills :

Python, Django, Redis, Celery, RabbitMQ, PostgreSQL, Kafka

Key Responsibilities :

• Design, develop, and maintain web applications using Python & Django.
• Implement asynchronous tasks and background job processing using Celery with RabbitMQ/Redis.
• Work with PostgreSQL for database design, optimization, and complex queries.
• Integrate and optimize messaging/streaming systems using Kafka.
• Write clean, scalable, and efficient code following best practices.
• Troubleshoot, debug, and optimize application performance.
• Collaborate with cross-functional teams (frontend, DevOps, QA) for end-to-end delivery.
• Stay updated with the latest backend development trends and technologies.

Requirements :

• Minimum 3+ years of experience in backend development using Python & Django.
• Hands-on experience with Redis, Celery, RabbitMQ, Kafka, and PostgreSQL.
• Strong understanding of REST APIs, microservices architecture, and asynchronous task management.
• Knowledge of performance tuning, caching strategies, and scalable system design.
• Familiarity with Git, CI/CD pipelines, and cloud deployment (AWS/GCP/Azure) is a plus.
• Excellent problem-solving and communication skills.

Description

Join company as a Backend Developer and become a pivotal force in building the robust, scalable services that power our innovative platforms. In this role, you will design, develop, and maintain server‑side applications, ensuring high performance and reliability for millions of users. You’ll collaborate closely with cross‑functional product, front‑end, and DevOps teams to translate business requirements into clean, efficient code, while participating in code reviews and architectural discussions. Our dynamic environment encourages continuous learning, offering opportunities to work with cutting‑edge technologies, cloud infrastructures, and modern development practices. As a key contributor, your work will directly impact product quality, user satisfaction, and the overall success of company's mission to streamline hiring solutions.

Requirements:

• 1–15 years of professional experience in backend development, with a strong focus on building APIs and microservices.
• Proficiency in server‑side languages such as Python, Java, Node.js, or Go, and solid understanding of object‑oriented and functional programming paradigms.
• Extensive experience with relational (e.g., PostgreSQL, MySQL) and NoSQL databases (e.g., MongoDB, Redis), including schema design and query optimization.
• Familiarity with cloud platforms (AWS, GCP, Azure) and containerization technologies like Docker and Kubernetes.
• Hands‑on experience with version control (Git), CI/CD pipelines, and automated testing frameworks.
• Strong problem‑solving abilities, effective communication skills, and a collaborative mindset for working within multidisciplinary teams.

Roles and Responsibilities:

• Design, develop, and maintain high‑throughput backend services and RESTful APIs that support core product features.
• Implement data models and storage solutions, ensuring data integrity, security, and optimal performance.
• Collaborate with front‑end engineers, product managers, and designers to define technical requirements and deliver end‑to‑end solutions.
• Participate in code reviews, provide constructive feedback, and uphold coding standards and best practices.
• Monitor, troubleshoot, and optimize production systems, implementing robust logging, alerting, and performance tuning.
• Contribute to the continuous improvement of development workflows, including CI/CD automation, testing strategies, and deployment processes.
• Stay current with emerging technologies and industry trends, proposing innovative approaches to enhance system architecture.

Budget:

• Job Type: payroll
• Experience Range: 1–15 years

Description :

Job Title : Python Engineer- AI Agents & Code Optimization

Experience : 2+ Years

Employment Type : Full-time

Location : Remote

About the Role :

We are looking for a hands-on Software Engineer to build and improve AI agents that work directly on our production code.

Your core responsibility will be to design and evolve a specialized AI agent that deeply understands our codebase and actively helps make it faster, cleaner, simpler, and cheaper to maintain.

This is not a research role. This is real work on real systems with real business impact.

How We Work :

- Business impact first : Cheaper, Faster, Better

- Simple beats complex always

- Small changes, shipped fast

- You own your work end-to-end

- First question is always : Do we even need this?

- Flat team, zero micromanagement

- Decisions can change adaptability matters

- No long PRDs : one clear goal ? discuss ? execute

- Ship, measure, improve, repeat

What You Will Do :

- Build and use AI agents to optimize, refactor, and remove code

- Feed logs, metrics, and performance data back into AI agents

- Profile applications and identify performance bottlenecks

- Optimize SQL queries and database usage

- Improve deployment pipelines and release processes

- Continuously improve internal AI tooling

- Work closely with infrastructure and production systems

Tech You Should Be Comfortable With :

You dont need to be an expert in everything, but you should be comfortable working with :

- Linux CLI (Required)

- Python

- PHP

- SQL (MySQL or MariaDB)

- Shell scripting

- Large Language Models (LLMs)

What Were Looking For :

- 2+ years of software engineering experience (or strong hands-on projects)

- Solid understanding of performance optimization

- Experience cleaning up legacy or messy codebases

- Practical profiling and debugging skills

- Comfortable working close to infrastructure and deployments

- Automation-first mindset

- Ability to explain technical decisions clearly and simply in English

Nice to Have :

- Experience building AI agents

- Exposure to large or long-running systems

- CI/CD or deployment automation experience

When You Join :

- Career Growth : You are expected to grow into a tech lead, entrepreneur, or highly skilled specialist

- Bleeding-Edge Tech : Hands-on experience with alpha/beta software, cutting-edge infrastructure, and top tier hardware

- Global Exposure : Work with a global team and directly with C-level leadership

- Real Impact : Your code directly solves real user problems and moves the company forward