Responsibilities

●

●

●

●

●

Own the end-to-end architecture of GenAI solutions across the retrieval, orchestration,

model, integration, and deployment layers.

Translate ambiguous business problems into AI solution designs with clear scope,

feasibility assessment and success metrics.

Define reference architectures, design patterns and reusable accelerators for RAG,

agentic workflows and LLM integration.

Lead model and platform selection, documenting the cost, latency, accuracy and

data-residency trade-offs behind each decision.

Design the non-functional envelope: scalability, latency budgets, availability,

observability and inference cost control.●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

Architect data and retrieval pipelines covering ingestion, chunking, embedding strategy,

vector store selection and hybrid search.

Define evaluation strategy and guardrails so accuracy, groundedness, safety and

hallucination rates can be measured and governed.

Embed security, privacy and compliance into the design: PII handling, tenancy isolation,

access control and audit.

Support pre-sales and discovery through solution workshops, effort estimation,

technical proposals and client presentations.

Guide delivery teams, run design reviews and mentor engineers, while staying hands-on

in prototyping and unblocking hard problems.

Maintain architecture documentation and decision records, and assess which advances

in generative AI are ready for enterprise adoption.

Own multiple client engagements simultaneously while maintaining delivery quality.

Lead discovery workshops, challenge assumptions, and refine business requirements

into technically sound solutions.

Push back on unrealistic timelines, architectures, or requirements using engineering

judgement and data.

Build strong relationships with Team, product owners, and executive stakeholders.

Mentor senior engineers and cultivate future architects and technical leaders.

Lead architectural governance, design reviews, and technical decision records.

Set engineering standards, coding guidelines, AI development best practices, and review

critical code.

Remain hands-on by building prototypes, solving difficult technical problems, and

contributing production-quality code when needed.

Drive cross-project reuse through internal frameworks, accelerators, and reference

implementations.

Present architecture, trade-offs, risks, and implementation strategy confidently to

executive audiences.

Essential Skills

Job

●

●

●

10+ years in software engineering, data or AI roles, including at least 3 years in an

architect or technical lead capacity.

Demonstrated experience architecting and delivering production Generative AI systems,

not only prototypes or POCs.

Strong hands-on Python, with the ability to prototype designs and review production

code.●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

Deep expertise in LLM application architecture: prompt and context engineering,

structured output, tool calling and orchestration.

Proven experience designing RAG systems end-to-end, including chunking, embedding

selection, hybrid retrieval and re-ranking.

Proven ability to manage multiple enterprise AI programs simultaneously.

Strong client-facing consulting experience with executive communication.

Excellent presentation, whiteboarding, and workshop facilitation skills.

Demonstrated experience influencing technical decisions across multiple teams.

Experience managing senior engineers and mentoring future technical leaders.

Strong engineering judgement balancing quality, cost, delivery timelines, and business

value.

Comfortable making architectural decisions with incomplete information.

Experience with agent and orchestration frameworks such as LangChain, LangGraph,

LlamaIndex or CrewAI.

Strong knowledge of vector databases (Pinecone, Weaviate, Qdrant, FAISS, pgvector)

and their operational trade-offs.

Solid machine learning and deep learning fundamentals, including fine-tuning and

adaptation approaches (LoRA/QLoRA, PEFT).

Strong cloud architecture skills on AWS, Azure or GCP , including their AI/ML and data

services.

Experience with microservices, API design, event-driven patterns and enterprise system

integration.

Working knowledge of MLOps and LLMOps: CI/CD, containerization, model versioning,

monitoring and rollback.

Experience defining LLM evaluation and observability approaches (RAGAS, LangSmith,

DeepEval or equivalent).

Personal

●

●

●

●

●

Strong communication and stakeholder management skills, including with non-technical

and client-side audiences.

Sound engineering judgement, with the confidence to defend a design and the

openness to revise it.

Strong ownership across the full delivery lifecycle, not only the design phase.

Ability to mentor engineers and lead through influence rather than authority.

Comfortable operating with ambiguity in a fast-moving technology space.

Preferred Skills

Job

●

Experience architecting multi-agent systems and complex autonomous workflows.●

●

●

●

●

●

●

●

Exposure to multimodal AI covering vision, speech or document understanding.

Experience with inference optimization and serving at scale (vLLM, TensorRT-LLM,

Triton, quantization).

Experience deploying open-weight models on-premise or in-VPC for data-sensitive

clients.

Knowledge of graph-based retrieval (GraphRAG) and knowledge-graph modelling.

Familiarity with AI governance and responsible AI frameworks (EU AI Act, NIST AI RMF,

ISO/IEC 42001).

Experience with data platform architecture and pipelines (Airflow, dbt, Spark, lakehouse

patterns).

Pre-sales, solutioning or client-facing consulting experience in a services organisation.

Domain depth in one or more of BFSI, healthcare, retail, supply chain or manufacturing.

Personal

●

●

Proactive mindset with a genuine interest in tracking a fast-moving field.

Consulting orientation, balancing technical ideals against client timelines and budgets.

Other Relevant Information

●

●

●

●

Bachelor's or Master's degree in Computer Science, Data Science, Engineering, or a

related field.

Relevant certifications in AI/ML, cloud architecture (AWS/Azure/GCP), or enterprise

architecture are a plus.

A portfolio of production Generative AI architectures, open-source contributions or

published work is highly desirable.

This role offers the flexibility of working remotely in India.

Leadership Expectations

●

●

●

●

●

Leads by example through technical excellence.

Creates an environment where engineers grow into technical leaders.

Encourages ownership, accountability, and continuous learning.

Provides constructive feedback and coaching.

Promotes pragmatic engineering decisions over unnecessary complexity.

LeewayHertz is an equal opportunity employer and does not discriminate based on race,

colour, religion, sex, age, disability, national origin, sexual orientation, gender identity, or any

other protected status. We encourage a diverse range of applicants.