Senior AI Engineer

Vibehackers; Navi Mumbai; Hybrid; INR 3,000,000 - 5,200,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Teradata is seeking a Senior AI Engineer to design and build production-grade agentic AI systems for enterprise deployments, with focus on multi-agent pipelines, memory management, and governance. Hybrid role based in Hyderabad, India.

You will work on tool-calling, evaluation frameworks, and red-teaming, ensuring reliability, safety, and measurable outcomes across enterprise workflows using Python and leading MLOps practices.

Qualifications

• BS/MS/PhD in Computer Science, AI/ML, or related field.
• 5+ years of software engineering experience, including 2+ years focused on LLM or agentic systems.
• Hands-on experience building and deploying production agentic systems.
• Proficiency in Python with strong typing, testing, and observability practices.

Responsibilities

• Design and implement multi-agent architectures: task decomposition, inter-agent communication, delegation, and coordination.
• Build agent harnesses: loop controllers, tool registries, execution sandboxes, and retry/fallback logic.
• Develop planning and reasoning frameworks (e.g., chain-of-thought, tree-of-thought) and integrate with enterprise workflows.
• Implement dynamic tool-calling pipelines, function invocation with schema validation, and robust error recovery.
• Design and implement end-to-end agent evaluation: taxonomies, success criteria, ground-truth datasets, multi-dimensional scoring, and LLM-as-judge systems with human-in-the-loop validation.
• Build trajectory-level evaluation tooling to analyze execution traces and design red-teaming/adversarial harnesses to probe failure modes.
• Instrument evaluation and production pipelines with cost, latency, and quality monitoring; establish regression suites for deployment gating.
• Design context and memory management systems: dynamic compression, sliding windows, priority eviction, multi-tier memory, indexing, lifecycle management, and privacy-aware scoping.
• Design reusable, composable agent skills and document automation capabilities and frontend artifact generation.
• Curate prompt libraries and use AI coding assistants as primary development tools while maintaining rigorous review, testing, and security practices.

Skills

Python

LLM/agentic systems

LangChain

Testing & observability

AI-assisted development

Education

BS/MS/PhD in Computer Science/AI/ML

Tools

LangGraph

AutoGen

CrewAI

MLflow

Weights & Biases

DVC

vLLM

TGI

Triton

OpenTelemetry

Datadog

Grafana

Job description

Explicitly requires vibe coding skills — expects using AI coding assistants (Claude Code, Copilot, Cursor) and natural-language-driven development.

About the Role

Teradata is hiring a Senior AI Engineer to design and build production-grade agentic AI systems, including multi-agent orchestration, memory/context management, evaluation frameworks, and governance for enterprise-scale deployments. The role focuses on hardening LLM-driven agents for reliability, safety, and measurable outcomes in hybrid work mode based in Hyderabad, India.

Job Description

Role

Senior AI Engineer responsible for architecting and implementing production-grade agentic systems (multi-agent pipelines, tool-calling, memory architectures, evaluation frameworks, and governance) for an AI-native enterprise platform.

Key Responsibilities

• Design and implement multi-agent architectures: task decomposition, inter-agent communication, delegation, and coordination.
• Build agent harnesses: loop controllers, tool registries, execution sandboxes, and retry/fallback logic.
• Develop planning and reasoning frameworks (e.g., chain-of-thought, tree-of-thought) and integrate with enterprise workflows.
• Implement dynamic tool-calling pipelines, function invocation with schema validation, and robust error recovery.
• Design and implement end-to-end agent evaluation: taxonomies, success criteria, ground-truth datasets, multi-dimensional scoring, and LLM-as-judge systems with human-in-the-loop validation.
• Build trajectory-level evaluation tooling to analyze execution traces and design red-teaming/adversarial harnesses to probe failure modes.
• Instrument evaluation and production pipelines with cost, latency, and quality monitoring; establish regression suites for deployment gating.
• Design context and memory management systems: dynamic compression, sliding windows, priority eviction, multi-tier memory (in-context, episodic vector retrieval, procedural memory), indexing, lifecycle management, and privacy-aware scoping.
• Design reusable, composable agent skills and document automation capabilities (DOCX, PPTX, XLSX, PDF) and frontend artifact generation (HTML/React components, visualizations).
• Curate prompt libraries and use AI coding assistants as primary development tools while maintaining rigorous review, testing, and security practices.

Requirements

• BS/MS/PhD in Computer Science, AI/ML, or related field.
• 5+ years of software engineering experience, including 2+ years focused on LLM or agentic systems.
• Hands-on experience building and deploying production agentic systems (not just prototypes).
• Proficiency in Python with strong typing, testing, and observability practices.
• Familiarity with agent frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or equivalent.

Preferred Qualifications

• Research or implementation experience in agent evaluation, reasoning, or memory-augmented LLMs.
• Familiarity with MLOps tooling (MLflow, Weights & Biases, DVC) and model serving/quantization (vLLM, TGI, Triton).
• Exposure to observability stacks (OpenTelemetry, Datadog, Prometheus/Grafana) and regulated-industry compliance requirements.
• Experience with multi-modal agents, cloud AI platforms (AWS SageMaker, Azure ML, GCP Vertex AI), GPU cluster management, and contributions to open-source agentic/LLM evaluation projects.
• Portfolio demonstrating AI-assisted development practices and strong critical review of AI-generated code.
• Work closely with AI architects, ML and platform engineers, product and UX, security/compliance, infrastructure (GPU/model serving), and customer success to deliver enterprise-ready agent solutions.

Location & Work Model

• Hybrid role based in Hyderabad, India, with a flexible work model.

Tools & Tech

• Languages & frameworks: Python, HTML, React
• MLOps & serving: MLflow, Weights & Biases, DVC, vLLM, TGI, Triton
• Observability & infra: OpenTelemetry, Datadog, Prometheus, Grafana, GPU cluster management

Skills

System Design Agent Architecture LLM Engineering Evaluation & Metrics Design Context & Memory Management Software Engineering Best Practices Testing & Observability Prompt Engineering AI-assisted Development (Vibe Coding) Collaboration & Cross-functional Communication Security & Compliance Awareness MLOps Practices