AI Engineer — LLM Applications

Concord Technosoft Pvt Ltd; Delhi; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Concord Technosoft Pvt Ltd is building production-grade language model integrations to extract structured data from documents and automate responses within client workflows.

The team focuses on robust retrieval pipelines, document understanding, and cost-efficient inference. Candidates should bring strong Python skills and practical experience with LLM APIs and retrieval or agent frameworks, with a sceptical, measurement-driven mindset.

Qualifications

• Strong Python and backend engineering experience.
• Practical experience with an LLM API and at least one retrieval or agent framework.
• Scepticism about your own output and ability to measure impact of changes.
• Good judgment on when a language model is the right tool or when a regex suffices.

Responsibilities

• Work on retrieval pipelines over client data, including chunking and embedding models.
• Develop and improve structured extraction from PDFs, invoices and documents feeding real systems.
• Build tool-using and agentive workflows with guardrails and human review where needed.
• Develop evaluation harnesses and regression suites to prevent production breakages.
• Optimize cost and latency: token budgets, caching, and model routing.

Skills

Python

Backend engineering

LLM API

Retrieval framework

Agent framework

Experimentation & measurement

Job description

We are putting language models into products that businesses run on — extracting structured data from unstructured documents, drafting replies inside messaging workflows, and answering questions over a client's own catalogue and records. That is a different discipline from demos: it has to be right, auditable and cheap enough to run at volume.

What you would work on

• Retrieval pipelines over client data — chunking, embeddings, vector search, reranking, and the evaluation to prove any of it works
• Structured extraction from PDFs, invoices, catalogues and scanned documents where the output feeds a real system
• Tool-using and agentic workflows that take actions in our platforms, with guardrails and human review where the stakes justify it
• Evaluation harnesses and regression suites, so a prompt change cannot quietly break production
• Cost and latency work — token budgets, caching, model routing, and knowing when a smaller model is the correct answer

What we are looking for

• Strong Python, and enough backend engineering to ship a service rather than a notebook
• Practical experience with an LLM API and at least one retrieval or agent framework, plus a clear view of where those frameworks get in the way
• Scepticism about your own output. If you cannot measure whether a change helped, you have not finished
• An instinct for when a language model is the wrong tool and a regular expression would do

Useful, not required

Fine-tuning or adapter training, OCR and document layout models, working with Indian-language text, or experience deploying models under real cost constraints.