Senior AI Engineer (Agentic Systems)

Experience : 6.00 + years

Salary : Confidential (based on experience)

Expected Notice Period : 7 Days

Shift : (GMT+05:30) Asia/Kolkata (IST)

Opportunity Type : Remote

Placement Type : Full Time Contract for 6 Months(40 hrs a week/160 hrs a month)

**(*Note: This is a requirement for one of Uplers' client - Auric AI)

**What do you need for this opportunity?

Must have skills required: evaluation tools, opentelemetry, Terraform, Docker, GCP, Kubernetes, Agent Orchestration Frameworks, agentic systems, FastAPI, LLM, rag, Azure, Python

Auric AI is Looking for:**** JOB DESCRIPTION -Senior AI Engineer (Agentic Systems) 7–8 years experience About We build AI and data solutions that help organizations turn their data into better decisions and automated workflows. Our teams design, build and run production-grade systems, from data platforms and machine-learning models to agentic AI applications, for clients across industries. We work in small, senior, cross-functional teams where each person owns their work from design through to production.

Role summary- We are looking for a Senior AI Engineer to design, build and operate agentic AI systems. You will turn large language models into reliable agents that plan, use tools, retrieve knowledge and complete multi-step tasks for real business use cases. The role needs strong software engineering as much as AI expertise: agents must be observable, evaluated, secure and cost-controlled in production, not just demos.

Key responsibilities Agent design & development Design and build LLM-based agents and multi-agent workflows, including planning, tool use, memory and reflection Implement tool and function calling against internal and external APIs, databases and enterprise systems, with least-privilege permissions Build retrieval-augmented generation (RAG) pipelines, including document ingestion, chunking, embeddings, hybrid search and re-ranking Select and combine models (commercial and open-weight) based on quality, latency, cost and data-residency requirements Reliability, evaluation & safety Define and automate evaluation suites for agents: task success, groundedness, tool-call accuracy, regression tests and human review loops Implement guardrails: input and output validation, prompt-injection defence, PII handling and human-in-the-loop approval for high-impact actions Instrument agents end to end (traces, token usage, latency, cost per task) and set up monitoring and alerting Engineering & production Package agents as secure, scalable services (APIs, containers) and deploy them on cloud platforms Own CI/CD, prompt and configuration versioning, and safe rollout of AI features (feature flags, A/B and shadow testing) Work with data engineers, data scientists and full-stack engineers to embed agent experiences into products Technical leadership Set AI engineering standards, reusable components and design patterns for the wider team Mentor engineers on LLM application design and review AI-related code Track the fast-moving agent ecosystem and turn promising techniques into tested, production-ready capabilities Engage with clients and stakeholders to shape use cases and explain technical trade-offs

Required qualifications & experience 7–8 years of professional software engineering experience, including at least 2–3 years building and shipping LLM or generative AI applications to production Hands-on experience building agentic systems: tool or function calling, multi-step planning, state and memory management, and orchestration frameworks (e.g., LangGraph, Semantic Kernel, AutoGen, CrewAI, OpenAI or Anthropic agent SDKs, or equivalent custom orchestration) Strong Python and solid API engineering (FastAPI or similar), async programming, testing and packaging Practical experience with RAG: embeddings, vector and hybrid search (e.g., Azure AI Search, Elasticsearch, pgvector, Pinecone, Qdrant), chunking strategies and retrieval evaluation Experience designing LLM evaluations and observability (e.g., LangSmith, Langfuse, Arize Phoenix, OpenTelemetry or custom harnesses) Experience with at least one major cloud platform (Azure, AWS or GCP) and its AI services Docker and CI/CD Good understanding of LLM security risks (prompt injection, data leakage, excessive agency) and how to mitigate them Bachelor''''s or Master''''s degree in Computer Science, AI, Engineering or a related field, or equivalent experience

Preferred qualifications Model Context Protocol (MCP) or similar standards for connecting agents to tools and data Fine-tuning or distilling smaller models serving open-weight models with vLLM or similar Experience with multimodal models (vision, speech, documents) Experience building AI solutions in a client-facing or consulting environment Familiarity with responsible AI frameworks and AI regulation (e.g., EU AI Act) Technology environment What success looks like First 90 days: understand our products and client use cases, and deliver a first agent to production with tracing, evaluation and guardrails First 6 months: agents running in several workflows with measurable task success rates, cost per task and user adoption Ongoing: a reusable agent toolkit and set of practices that let the team ship new AI features quickly and safely Key competencies Ownership: takes responsibility for outcomes from design through to production Quality mindset: writes tested, maintainable, well-documented work Clear communication: explains technical ideas to technical and business audiences Collaboration: works across disciplines in a small, fast-moving team Continuous learning: keeps up with new tools and practices and applies them pragmatically What we offer The opportunity to work on cutting-edge AI and data projects with real business impact A modern cloud, data and AI technology stack A small, senior, collaborative team with direct access to decision makers Competitive salary and benefits, and support for training and certifications Hybrid working arrangements How to apply Please send your CV and a short cover letter describing a relevant project you have delivered, to [application e-mail / careers page]. Applications are reviewed on a rolling basis.

How to apply for this opportunity?

• Step 1: Click On Apply! And Register or Login on our portal.
• Step 2: Complete the Screening Form & Upload updated Resume
• Step 3: Increase your chances to get shortlisted & meet the client for the Interview!

About Uplers: Our goal is to make hiring reliable, simple, and fast. Our role will be to help all our talents find and apply for relevant contractual onsite opportunities and progress in their career. We will support any grievances or challenges you may face during the engagement.

(Note: There are many more opportunities apart from this on the portal. Depending on the assessments you clear, you can apply for them as well).

So, if you are ready for a new challenge, a great work environment, and an opportunity to take your career to the next level, don't hesitate to apply today. We are waiting for you!