AI Engineering Lead

Chimera Technologies Pte Ltd; Bengaluru; On-site; INR 3,500,000 - 7,500,000; Full time

Benefits offered by this job

Insurance benefits

Fortnightly tech talks

Can participate in innovation programs

Opportunity to work across multiple IS

Job summary

Chimera Technologies Pte Ltd in Bengaluru seeks a technical escalation owner for an AI agents platform who will handle incidents, implement permanent fixes, and mentor the operations team. The role blends escalation support with engineering delivery in a rotating shift and involves code writing.

Candidate must have hands-on experience in production systems, Python or Go, LangChain, and GitOps tooling like ArgoCD, with strong knowledge of Kubernetes and observability practices.

Qualifications

• 6+ years in software engineering with recent experience operating production systems.
• Strong programming ability in Python or Go, at production standard.
• Agent framework experience at architecture level — LangChain or equivalent.
• RAG systems in production: embedding pipelines, vector stores, retrieval quality.
• Distributed systems debugging across services and asynchronous boundaries.
• OpenTelemetry, distributed tracing and production observability design.
• IAM and access architecture — SSO, RBAC, privileged access.
• Kubernetes in production — workload design, resource management, scaling, failure modes.
• ArgoCD or equivalent GitOps tooling — pipeline design, release and rollback strategy.
• Demonstrated experience as the final technical escalation point for a live system.

Responsibilities

• Own complex troubleshooting and root cause analysis as the final escalation point.
• Debug the platform at code level — agent orchestration, retrieval and embedding paths, model routing, gateway and integration layers.
• Diagnose and resolve performance issues: latency, throughput, token and inference cost, resource contention.
• Deliver permanent fixes through the client's SDLC, change and release process.
• Own the deployment path — GitOps / AgroCD pipelines, release strategy, rollback design and environment promotion.
• Design and review AWS and Kubernetes architecture: workload placement, scaling, networking, cost and resilience.
• Design and review architecture changes, new integrations and connectors.
• Scope, estimate and deliver change requests and enhancements.
• Lead the automation and self-healing track, from candidate identification to deployment.
• Own observability and IAM architecture — instrumentation, alert routing, SSO and RBAC design.
• Mentor operations engineers and hold escalation cover for the shift that runs without a Lead on seat.

Skills

Python

Go

LangChain

RAG systems

OpenTelemetry

IAM

Kubernetes

ArgoCD

GitOps

Production debugging

Tools

Kubernetes

ArgoCD

GitOps

Job description

Technical escalation owner for an AI agents platform. Takes the incidents nobody else can resolve, establishes true root cause, and ships the permanent fix. Also the design authority for changes, integrations and automation, and the technical mentor for the operations team.

This is a mixed role: escalation support and engineering delivery in the same seat, on a rotating shift. It writes code. Candidates whose recent experience is limited to architecture review and estimation will not be a fit.

Responsibilities

• Own complex troubleshooting and root cause analysis as the final escalation point
• Debug the platform at code level — agent orchestration, retrieval and embedding paths, model routing, gateway and integration layers
• Diagnose and resolve performance issues: latency, throughput, token and inference cost, resource contention
• Deliver permanent fixes through the client's SDLC, change and release process
• Own the deployment path — GitOps / AgroCD pipelines, release strategy, rollback design and environment promotion
• Design and review AWS and Kubernetes architecture: workload placement, scaling, networking, cost and resilience
• Design and review architecture changes, new integrations and connectors
• Scope, estimate and deliver change requests and enhancements
• Lead the automation and self-healing track, from candidate identification to deployment.
• Own observability and IAM architecture — instrumentation, alert routing, SSO and RBAC design
• Mentor operations engineers and hold escalation cover for the shift that runs without a Lead on seat.

Requirements

• 6+ years in software engineering, with recent, direct experience operating production systems
• Strong programming ability in Python or Go , at production standard
• Agent framework experience at architecture level — LangChain or equivalent: orchestration, tool-calling, memory, retrieval
• RAG systems in production: embedding pipelines, vector stores, retrieval quality and failure modes
• Distributed systems debugging across services and asynchronous boundaries
• OpenTelemetry , distributed tracing and production observability design
• IAM and access architecture — SSO, RBAC, privileged access
• Kubernetes in production — workload design, resource management, scaling, failure modes
• ArgoCD or equivalent GitOps tooling — pipeline design, release and rollback strategy, environment promotion
• Demonstrated experience as the final technical escalation point for a live system

Good to have

• Both Python and Go
• Temporal or another durable workflow engine, at design level
• Prompt and retrieval optimisation.
• Service mesh, and progressive delivery patterns such as canary or blue-green
• Participate in several organization wide programs, including a compulsory innovation based Continuous improvement program providing you platforms to showcase your talent.
• Insurance benefits for the self and the spouse including maternity benefits.
• Ability to work on many products as the organization is focusedon working with several ISVs.
• Fortnightly sessions to understand the directions of each function and an opportunity to interact with the entire hierarchy of the organization.
• Celebrations are a common place - physical or virtual. Participate in several games with your coworkers.
• Voice your opinions on topics other than your work - Chimera Talks.