Senior AI Engineer

Ipeople Infosysteams LLC

Bengaluru, INhybridPosted Jul 9, 2026
Posting intelligenceActively listed

Skills

classificationdatabricksregressionlangchaintableaugrafanapythonopenaiawsllmml

About the role

Role Title: Senior AI Engineer

Location : Bangalore (Hybrid)

Contract duration: 6 Months

Minimum Experience

8+ years AI/ML/software engineering, 2+ years LLMOps/GenAI experience

Key Skills

AI/ML, GenAI, LLMOps, Routing Intelligence, Intent Classification, Token Governance, Cost Optimization, AI Observability

Role Summary

We are looking for a Senior AI Engineer to design and build App Routing Intelligence Layer and AI cost governance capabilities.

The routing layer should determine whether a user request can be handled by a deterministic API, guided workflow, cached response, clarification step, or MuleSoft Agent Fabric. This role is responsible for building the intelligence that enables App to route requests efficiently without making unnecessary LLM calls.

The ideal candidate should have strong experience with intent classification, AI routing, LLMOps, evaluation, observability, cost controls, and enterprise AI governance.

Key Responsibilities

Design and build the App Routing Intelligence Layer.

Implement API-first routing logic to reduce unnecessary LLM usage.

Build intent classification and routing strategies using rules, catalogs, lightweight classifiers, and confidence scoring.

Define when ARMI should route to:

API Engine

Guided workflow

MuleSoft Agent Fabric

Notification Engine

Clarifying question

Access denied / policy block

Define and manage the intent catalog, API action catalog, agent catalog, and routing rules.

Build cost-aware routing logic to minimise token consumption.

Design token usage tracking across users, teams, business groups, channels, agents, and models.

Build telemetry requirements for the token dashboard.

Define metrics such as LLM avoidance rate, API-first completion rate, agent escalation rate, cache hit rate, and cost per interaction.

Build evaluation datasets to test routing quality and prevent regressions.

Collaborate with the Full Stack Developer to implement routing APIs and telemetry persistence.

Collaborate with the Agent Orchestration AI Engineer to ensure proper handoff into MuleSoft Agent Fabric.

Define caching, summarisation, memory selection, and prompt optimisation strategies where AI is used.

Establish model selection guidelines and cost-control policies.

Support governance, auditability, and explainability of routing decisions.

Required Skills

Strong experience with AI/ML engineering, LLM applications, or intelligent routing systems.

Strong Python experience.

Experience building intent classification, semantic routing, rules-based routing, or hybrid routing systems.

Strong understanding of LLM cost drivers, token management, prompt optimisation, and context management.

Experience designing AI observability and LLMOps processes.

Experience with AI evaluation, test datasets, regression testing, and quality metrics.

Understanding of API-first architecture and enterprise workflow automation.

Experience with embeddings, vector search, semantic similarity, or lightweight classification techniques.

Experience designing routing decision objects and confidence-based routing.

Experience with telemetry, analytics, dashboards, and usage reporting.

Understanding of RBAC, policy checks, data security, and enterprise governance.

Ability to design systems that avoid LLM calls unless they are truly needed.

Preferred Skills

Experience with MuleSoft, MuleSoft Agent Fabric, or enterprise integration platforms.

Experience with Microsoft AI Foundry, AWS Bedrock, Databricks, or OpenAI-compatible AI services.

Experience with model gateways, AI gateways, or centralised LLM access layers.

Experience with prompt management, model routing, and cost optimisation.

Experience with tools such as LangChain, LlamaIndex, Semantic Kernel, MLflow, Weights & Biases, Arize, LangSmith, or OpenTelemetry.

Experience with dashboard tools such as Power BI, Grafana, Tableau, or custom analytics dashboards.

Experience implementing AI guardrails, policy engines, or governance workflows.

Experience with enterprise search, knowledge bases, and RAG evaluation.

Experience with ServiceNow, SuccessFactors, Microsoft Graph, or similar enterprise APIs.

Ideal Candidate Profile

The ideal candidate is a senior AI engineer who is highly practical and cost-conscious. They should understand that not every user request requires an LLM and should be capable of designing intelligent, governed routing that prioritises APIs, workflows, and deterministic execution before using AI agents.

Best regards,

Swapnil Thakur

Recruitment & Delivery Lead

iPeople Infosystems LLC

Contact No: +91 7972726448

Email ID: swapnil.t@ipeopleinfosystems.com

Visit us at www.ipeopleinfosystems.com

Pay: ₹180,000.00 - ₹210,000.00 per month

Work Location: Hybrid remote in Bengaluru, Karnataka

Questions about this role

Click "Apply with AI Applyd" above. We auto-fill the application from your resume and answer screening questions in seconds. No copy and paste, no juggling tabs.

Compensation for Machine Learning Engineer roles in India varies widely by seniority, employer size, and remote vs onsite arrangement. Check the salary range on this listing when published, or browse our Machine Learning Engineer hub for India medians across recent openings.

Most applications complete in under 90 seconds. You can track the status in your dashboard and watch the screenshot proof land the moment the application submits.

AI Applyd supports Greenhouse, Lever, Ashby, Workday, iCIMS, SmartRecruiters, Personio, Teamtailor and other major ATS platforms. If we can submit through the platform, we do.

Want AI Applyd to auto-apply to roles like this?

We tailor your resume per posting, fill the forms, and track replies for you.