Senior Software Engineer - AI & Knowledge System - Noida

NeoXam; Hinoba-an; On-site; PHP 994,000 - 1,392,000; Full time

Job summary

NeoXam in Noida, India is seeking a Senior Software Engineer specialized in GenAI and knowledge systems to own a strategic, greenfield initiative across AI, software engineering, and knowledge management. You will explore, prototype, and evolve toward a production-grade system with real use cases.

This hands-on role is individual contributor with end-to-end ownership, from architecture to deployment, with potential to grow a team as the project matures.

Qualifications

• 5-8 years of software engineering experience.
• 5+ years Python development experience, incl. FastAPI.
• Hands-on experience building AI/ML or data pipelines in production.
• Experience designing agent evaluation frameworks and eval harnesses.
• Hands-on with RAG architectures and LLM frameworks.
• Working knowledge of vector databases and embeddings.
• Cloud-native AI platform experience (AWS/Azure/GCP).
• Familiarity with Claude Code or equivalent agentic env.

Responsibilities

• Design and deploy a RAG-based knowledge service.
• Build agentic tooling for LLM agents across heterogeneous corpora.
• Develop pipelines synthesizing knowledge artifacts from code/docs/configs.
• Define and maintain a domain ontology for NeoXam products.
• Improve retrieval quality, agent reasoning, and reliability.

Skills

Python development

Backend development

FastAPI

AI/ML pipelines

LLM frameworks

RAG architectures

LangChain

Weaviate

Pinecone

Tools

LangChain

LlamaIndex

Semantic Kernel

Pinecone

Weaviate

pgvector

Job description

Role - Senior Software Engineer -AI Engineer & Knowledge Systems (GenAI / Agentic AI)

Location: India - Noida

Type: Full-time

R&D Technology

About NeoXam

NeoXam is a leading B2B fintech software vendor serving buy-side investment managers and asset servicers globally. Our platform covers data management, reconciliation, fund accounting, reporting, and portfolio management. As we scale, we are investing in making our knowledge, both technical and functional, structured, queryable, and continuously up to date.

The Role

We are looking for a GenAI Engineer to own a strategic, greenfield initiative at the intersection of AI, software engineering, and knowledge management.

The problem space is clear: make NeoXam's technical and functional knowledge accessible, reliable, and actionable across engineering, support, and product teams. The exact shape of the solution is yours to define. You will explore, prototype, and progressively converge toward a production-grade system grounded in real use cases.

This is a hands-on individual contributor role with end-to-end ownership, from architecture to deployment. As the initiative matures, you will have the opportunity to grow a team around you.

What You Will Work On

• Design and deploy a RAG-based knowledge service, including ingestion pipelines consolidating information from codebases, documentation, and structured data

• Build agentic tooling enabling LLM agents to navigate and reason over large, heterogeneous technical corpora

• Develop pipelines that synthesize knowledge artifacts at multiple levels of abstraction from low-level technical references to functional and business-oriented content

• Define and maintain a domain ontology capturing NeoXam's product concepts and their relationships

• Continuously improve retrieval quality, agent reasoning, and output reliability based on real usage

Why This Problem Is Hard

• Highly heterogeneous inputs: code, documentation, financial data, configurations

• Strong correctness expectations with multi-level reasoning technical, functional, business

• Constantly evolving knowledge across projects and clients

• Outputs must be explainable and trustworthy not black-box answers

What We Are Looking For

• 5-8 years of software engineering experience

• Must Have 5+ years Python development experience, in backend or systems engineering roles, including modern API frameworks such as FastAPI

• Hands on experience building and shipping AI, ML, or data pipelines in production

• Experience designing agent evaluation frameworks - creating eval datasets, test scenarios, metrics, automated regression tests, and quality gates - and evaluating agents beyond final-answer accuracy, including planning, tool use, reasoning trajectory, reliability, safety, latency, and cost (Langfuse, LangSmith, Ragas, or custom eval harnesses)

• Hands on experience with RAG architectures and LLM frameworks (LangChain, LlamaIndex, Semantic Kernel, or equivalent)

• Working knowledge of vector databases (Pinecone, Weaviate, pgvector, or equivalent) and embeddings/semantic search;

• GraphRAG experience is a plus

• Hands on experience with at least one cloud-native AI platform (AWS Bedrock, Azure AI Foundry, or GCP Vertex AI)

• Comfortable working end-to-end autonomously, from architecture to deployment

• Fluency with Claude Code, Cursor, or an equivalent agentic development environment

Who You Are

• A builder, energized by greenfield problems

• Pragmatic, you pick the right tool, not the flashiest one

• Autonomous, you drive toward outcomes without waiting to be told what to do next

• Curious, you find the intersection of LLMs and software systems genuinely interesting

Why Join

• Full ownership of a strategic, company-wide initiative, you design the architecture, you make the calls

• Direct visibility at the highest level of product and engineering

• Path to building and leading a team as the scope grow