You are a Machine Learning Engineer with strong programming skills in Python and JavaScript/TypeScript (Node.js), comfortable applying modern ML practices to real-world product workflows. This is a hybrid role at the intersection of AI/ML engineering and software development - you'll be working not just with models, but also on the systems that bring them to life in production environments.

? What you'll do:
In the early stages, focus on building robust backend APIs and microservices to support key business logic - including authentication, subscriptions, usage tracking, and user management.
Gradually shift into designing and implementing the core agent and LLM workflow logic, including memory, context-awareness, multi-agent collaboration, tool calling and many more.
Collaborate on integrating multiple LLM providers (OpenAI, Claude, Gemini, OpenRouter, etc.) into the routing system, supporting structured output and external tool interactions
Work with vector databases (Qdrant, Pinecone, Chroma, Faiss) and use efficient RAG techniques for code-aware reasoning and search
Partner with frontend and backend engineers to create seamless user-facing developer experiences across our products
Contribute to technical design discussions and help evolve the architecture to support both AI workflows and broader platform needs
You may also be involved in other ML or AI-related product initiatives, depending on the direction of parallel projects

??? Your engineering Superpowers:
Commercial experience 3+ years of commercial experience working in ML/AI product environments
Strong programming skills in Python and JavaScript/TypeScript (Node.js)
Proven ability to write clean, maintainable, and well-tested code (unit testing as part of your process)
Applied experience with NLP/LLM models, especially transformer-based architectures
Proficiency in designing, executing, and maintaining AI/ML systems and solutions in a production environment
Hands-on experience building and optimizing LLM-based workflows: agent and multi-agent systems, context-awareness, persistence, memory, prompt engineering, structured output, tool use
Familiarity with agentic and agent orchestration frameworks (LangGraph, LangChain, LlamaIndex, AutoGen, PyDantic AI, smolagents, etc.)
Experience working with LLM provider APIs (e.g. OpenAI, Anthropic, Gemini, OpenRouter) for prompt execution, tool calling, and structured outputs
Experience working with vector databases, RAG strategies, and hybrid search techniques
Exposure to observability tools (LangSmith, Langfuse, Traceloop, MLFlow, etc.) for evaluating and improving AI behavior in production
Good knowledge of SQL/NoSQL databases and data modeling
Strong software engineering fundamentals - including GitOps, CI/CD, Docker; familiarity with Kubernetes is a plus
Prior use of AI code editors or developer productivity tools

? Conditions and bonuses:
A unique opportunity to lead and shape the launch of a new brand
Work in a dynamic and innovative Tech AI environment
Competitive salary package
Generous budgets for initiatives and growth opportunities
Vacation days 25, additional days off, and sick leave
Flexible working options: remote or hybrid in one of our offices
Clear paths for professional and career growth

@tata_babi