AI/ML Engineer (Noida, India)

Terriqon; Dadri; On-site; INR 480,000 - 720,000; Full time

Benefits offered by this job

Direct access to senior engineers

Founder access

Growth opportunities

Job summary

Terriqon is hiring an AI/ML Engineer in Noida, India to design and build RAG pipelines and agentic AI workflows that run in production. You will work with LLMs, vector search, and tool-using agents, prioritising reliability and evaluation alongside demos.

The role requires 2+ years in AI/ML or Python software engineering, with hands-on RAG and vector database experience, and a strong grasp of prompts, tooling, and model selection.

Qualifications

• 2+ years of AI/ML or software eng with Python.
• Hands-on experience building RAG systems with embeddings and a vector DB.
• Experience building agents that use tool or function calling.
• Practical experience with LLM APIs and prompt design.
• Ability to measure and improve quality, not just prototypes.

Responsibilities

• Design and build RAG pipelines: ingestion, chunks, embeddings, vector search, reranking.
• Build agentic AI workflows with tool calls and multi-step reasoning.
• Work with LLM APIs and open models; choose best model for tasks.
• Evaluate output quality, latency and costs with clear metrics.
• Add guardrails, logging and monitoring for production reliability.
• Collaborate with backend to ship AI features as APIs.

Skills

Python

AI/ML

RAG systems

Agentic AI workflows

LLM APIs

Tools

LangChain

LlamaIndex

pgvector

Qdrant

Pinecone

Job description

About us

Terriqon is a field data platform for organisations that collect data in the field – NGOs, M&E teams and programme teams. Field teams collect data on a mobile app that works offline, and Terriqon's AI turns that data into donor and programme reports in minutes instead of weeks.

Terriqon is built by EPixelSoft, a software engineering company based in Noida with 12+ years of experience and 700+ projects delivered. You will join our engineering team in India.

The role

We are looking for an AI/ML Engineer to design and build RAG (retrieval-augmented generation) systems and agentic AI workflows that run in production.

You will work with LLMs, vector search and tool-using agents, and you will care as much about evaluation and reliability as about getting a demo to work.

Type: Full-time, based in Noida, India.

Compensation: Monthly salary paid in Indian Rupees (INR), based on your experience and discussed at interview.

What you will do

• Design and build RAG pipelines: document ingestion, chunking, embeddings, vector search, retrieval and reranking
• Build agentic AI workflows with tool calling, multi-step reasoning and orchestration
• Work with LLM APIs and open models, and choose the right model for each task
• Evaluate and improve output quality, latency and cost using test sets and clear metrics
• Add guardrails, logging and monitoring so AI features are safe and reliable in production
• Work with the backend team to ship AI features as production APIs

Must have

• 2+ years of experience in AI/ML or software engineering with Python
• Hands-on experience building RAG systems with embeddings and a vector database
• Experience building agents that use tool or function calling
• Practical experience with LLM APIs and prompt design
• Ability to measure and improve quality, not just build prototypes

Strong advantage

• Experience with frameworks such as LangChain or LlamaIndex, or with building your own orchestration
• Experience with vector stores such as pgvector, Qdrant or Pinecone
• Experience with LLM evaluation tooling, fine-tuning or open-source models
• Experience deploying services on AWS or another cloud

What we offer

• A monthly salary paid in INR
• Work on AI features that ship to real users, not just prototypes
• Direct access to senior engineers and the founder
• Room to grow as our AI work expands

Only shortlisted candidates will be contacted.