AI Engineer
Build AI applications that perform reliably in production, with quality and cost measured from day one.
Job Description
- Role
- AI Engineer
- Role description
- Design, build and improve applications on large language models, including retrieval, tools and evaluation, with quality, latency and cost measured throughout.
- Must-have skills
- Python or TypeScript, LLM APIs, retrieval (RAG), evaluation and production software practice
- Good-to-have skills
- Fine-tuning, vector databases, observability tooling such as Langfuse or LangSmith, and MCP
- Minimum experience
- 2 to 6 years
- Educational qualification
- A degree in computer science, engineering or a related field, or equivalent practical experience
Summary
As an AI Engineer at Thinqmesh, you will build the applications that put AI to work: assistants that answer from an organisation's own knowledge, systems that read documents, and features that make everyday software smarter. You will care as much about how a system behaves on its worst day as on its best.
You will work with people who treat AI as engineering. That means test sets, measured results and honest conversations about what a model can and cannot do, so what you build is something people can trust.
Why This Role Matters Now
AI Engineer has become one of the fastest-growing job titles in technology, and the role has matured quickly. Employers now look for far more than the ability to call an API: they want evaluation, observability and cost control as core skills, because those are what separate a working product from an impressive demo.
Roles and Responsibilities
You will design and build LLM-powered applications, choosing models and architecture to suit the problem. You will build retrieval over private data, connect tools and structured outputs, and tune the whole system for accuracy, speed and cost.
You will create evaluation suites from real cases and run them on every change, so that improvements are proven and regressions are caught early. Once a system is live, you will monitor how it performs and use what you see to improve it.
You will work with product and client teams to decide where AI truly helps, and you will say so clearly when simpler software is the better answer.
- Design and build applications on large language models
- Build retrieval over private data and connect tools and structured outputs
- Create evaluation suites from real cases and run them on every change
- Tune systems for accuracy, speed and cost
- Monitor live systems and improve them from what you see
Professional and Technical Skills
You bring at least two years of software engineering with strong Python or TypeScript, and experience shipping applications on LLM APIs. You understand embeddings, retrieval, prompting and tool use, and you have measured model quality with real evaluations rather than impressions.
Experience with vector databases, fine-tuning, tracing tools such as Langfuse or LangSmith, or MCP will help you move quickly. Above all, you are curious, you test your assumptions and you explain your reasoning well.
- 2 or more years of software engineering
- Strong Python or TypeScript
- Experience shipping on LLM APIs
- Working knowledge of embeddings, retrieval and prompting
- Quality measured through evaluations rather than impressions
Tools You Will Use
- Python
- TypeScript
- OpenAI
- Claude
- Gemini
- Hugging Face
- LangChain
- PostgreSQL
- Docker
- GitHub
Additional Information
This role is hybrid or remote. It is full time in Noida, and a consultant role in San Francisco, Tustin and London. You will work closely with the client teams and colleagues you support.
We read every application ourselves. Show us something you have built or shipped, because real work gives us far more to talk about than a list of tools.
Stay Connected
Introduce Yourself
Tell us what you do best, and we will keep you in mind as roles open.