Generative AI Engineer

Senior Generative AI Engineer — Python / RAG / Agentic AI

India | Fully Remote | Full Time Contract | 6–12 Months | Up to $20 USD/hour

I’m recruiting an experienced, hands-on GenAI Engineer for a global biopharmaceutical client.

This role suits someone with an established background in Python software engineering, machine learning or data science who has gone on to build and deploy commercial LLM applications.

You should be comfortable taking a business requirement through technical design, coding, testing and deployment. You will work within an existing engineering team, but need to take ownership of your implementation and explain your technical decisions clearly.

The work will involve:

• Building Python services and APIs for GenAI applications.
• Developing RAG pipelines over documents and structured business data.
• Building agents that retrieve information, call tools and execute multi-step workflows.
• Integrating LLM applications with databases, APIs and enterprise systems.
• Evaluating answer quality, investigating failures and improving reliability.
• Deploying and supporting applications in cloud environments.

Essential Experience:

• At least five years of commercial experience in software engineering, ML engineering or applied data science, including substantial hands-on Python development.
• Around two years or more of commercial GenAI/LLM application development.
• Personal responsibility for significant components of at least one GenAI application used in production by business users or customers.
• Strong Python backend development, ideally FastAPI or a comparable API framework.
• Practical RAG experience covering ingestion, document processing, chunking, embeddings, vector retrieval and grounded answers.
• Commercial agent or workflow orchestration using LangGraph, LangChain or an equivalent framework, including custom Python implementations.
• SQL, structured and unstructured data, and external API integration.
• Experience testing LLM outputs, diagnosing retrieval or tool failures and implementing appropriate validation and access controls.
• Cloud deployment experience with AWS, Azure or GCP, plus Docker and version-controlled delivery.

Useful additional experience:

• Natural-language-to-SQL and conversational analytics.
• MCP servers and tool integration.
• Hybrid retrieval, reranking and retrieval evaluation.
• LLM tracing, evaluation datasets and regression testing.
• An earlier background in production ML, NLP, recommendation systems or predictive modelling.
• Palantir Foundry/AIP - Palantir experience is a bonus, not a requirement.

This is a development role. Courses, personal projects, prompt writing, LLM response evaluation or low-code configuration alone will not meet the requirement.

Contract details:

• Based in India, working fully remotely.
• Initial engagement of 6–12 months.
• Full-time: 40 hours per week during agreed team working hours.
• Rate up to $20 USD/hour, depending on relevant experience.
• Independent contractor arrangement.
• Start as soon as possible; please state your exact availability.
• You must be able to give the assignment full-time commitment. This is not suitable as additional work alongside an existing full-time job.

To apply, please send your CV and confirm:

• Current location.
• Earliest full-time start date and notice period.
• Required hourly rate in USD.
• Total commercial engineering/ML experience and commercial GenAI experience.
• One production GenAI application: what it does, what you personally coded, the stack, and who uses it.