Back to Jobs

Artificial Intelligence Engineer

Actively Reviewing

Occams Advisory

Dehradun Full-Time 2–4 yrs exp Posted 8 hours ago · Apply by Sep 14, 2026

Job Description

A. Company Overview

Founded in 2012, Occams Advisory is a leading business solutions, professional services and financial advisory provider specializing in growth, financing, and taxation. Serving as a trusted advisor throughout the business lifecycle, Occams combines Fortune 500 expertise, entrepreneurial insights, and a global perspective to deliver world-class solutions. Occams has achieved remarkable recognition for its rapid growth, securing 8 spots on Inc. magazine’s Fastest Growing 5000 Private Companies list, 4 consecutive rankings on the Financial Times Fastest Growing 500 Companies in the Americas. In 2023, Occams was honored on Fortune’s inaugural list of the 300 Most Innovative Companies. Operating across all U.S. states and territories, Occams boasts a team of over 100 professionals based in major cities worldwide, including New York, Los Angeles, Toronto, Delhi and Mumbai. Its leadership includes alumni from Fortune 500 companies such as Barclays, UBS, and Merrill Lynch, and prestigious academic institutions like NYU, Duke University, and London Business School. Recognized as a leader in professional services, Occams delivers transformative growth and advisory solutions to clients.

B. About Your Role

We are looking for an AI Engineer to join our AI Initiative, focused on building agentic infrastructure and multi-agent systems that power real business workflows across our product suite.

This role is for someone who has moved past experimenting with LLMs in notebooks and has actually shipped backend systems that call LLM APIs in production — someone comfortable with API integrations, orchestration logic, and the plumbing that makes agentic systems reliable, not just impressive in a demo.

You will own the backend integration layer connecting our products to LLM providers (Anthropic, OpenAI) and be responsible for designing, prototyping, and hardening multi-agent architectures — from a single tool-calling agent to coordinated multi-agent workflows with memory, retrieval, and task handoff.

C. Key Responsibilities

Build Multi-Agent Architectures: Design and prototype multi-agent structures — planner/executor patterns, tool-calling agents, agent-to-agent handoff — using the Anthropic API and OpenAI API.
Backend & API Integration: Build and maintain secure, scalable backend services and RESTful APIs that integrate LLM capabilities into existing products and workflows.
Agentic Infrastructure: Develop the supporting infrastructure for agents — orchestration logic, state/session management, tool/function-calling frameworks, and error handling/retry logic for LLM calls.
RAG & Memory Systems: Implement retrieval-augmented generation pipelines, including vector database integration (e.g., Qdrant) and memory modules, to improve agent accuracy and context retention.
Prompt & Tool Design: Apply advanced prompt engineering and tool/function schema design to ensure agents behave predictably and produce business-aligned outputs.
Cross-Functional Collaboration: Work closely with product managers and engineering leads to translate business requirements into working agentic prototypes, iterating quickly based on feedback.
Performance, Monitoring & Guardrails: Monitor, debug, and optimize agent/API performance in production, maintaining rigorous guardrails around cost, latency, and output quality.

D. Required Qualifications & Experience

Education:

Bachelor's or master's degree in Computer Science, Data Science, Engineering, or a related field; relevant certifications are a plus.

Experience:

1–2 years of hands-on experience building backend systems that integrate LLM APIs — academic, internship, or professional experience is acceptable, provided it includes real, working implementations (not only coursework/theory).

Essential Technical Skills:

Working experience with the Anthropic API and/or OpenAI API, including function/tool calling.
Hands-on experience building or prototyping multi-agent systems (e.g., agent orchestration frameworks, LangChain, LangGraph, CrewAI, AutoGen, or custom orchestration).
Strong backend development skills in Python or Node.js, with experience building and securing RESTful APIs and microservices.
Practical understanding of RAG pipelines and vector databases (e.g., Qdrant, Pinecone, Weaviate).
Solid grasp of LLM fundamentals — transformers, embeddings, context windows, token/cost management.
Experience with cloud platforms (AWS, Azure, or Google Cloud) for deploying AI-backed services.
Comfort working with datasets for AI-related tasks, and debugging/optimizing live LLM-powered systems.

Preferred Skills:

Prior experience shipping an agentic product feature (not just a personal project) into a live environment.
Experience with observability/tracing tools for LLM applications (e.g., LangSmith, Helicone).
Strong problem-solving skills and ability to work directly with product and business stakeholders.

E. Benefits & Perks