AI Engineer

Key Responsibilities

AI & GenAI Engineering

Design and build production-grade AI/ML and

LLM-powered applications

.

Develop

RAG systems

using embeddings, semantic search, vector databases, retrieval, and reranking.

Build tool-calling, workflow-based, and

agentic AI systems

where appropriate.

Work with ML/DL models, LLMs, and multimodal models based on application requirements.

Implement evaluation, validation, guardrails, and fallback mechanisms for AI applications.

Optimize AI systems for

quality, latency, reliability, scalability, and cost

.

Software Engineering & System Design

Build maintainable production services using

Python and Go (Golang)

.

Design and develop REST/gRPC APIs and reusable backend components.

Design scalable and reliable architectures for AI applications.

Apply system design and distributed-system principles to make appropriate architectural decisions.

Work with databases, caching, messaging, and supporting backend infrastructure.

Follow strong engineering practices around testing, code reviews, version control, and documentation.

Production Deployment & Infrastructure

Deploy and operate AI applications in production using

Docker

and cloud platforms such as

AWS, Azure, or GCP

.

Build and maintain

CI/CD pipelines

and production deployment workflows.

Work with

Kubernetes

or equivalent orchestration technologies.

Implement logging, monitoring, tracing, configuration, secrets management, and reliable rollback strategies.

Troubleshoot production issues across AI, application, and infrastructure layers.

Continuously improve system performance, reliability, and infrastructure efficiency.

Required Skills

2+ years

of relevant AI/ML or Software Engineering experience.

Strong programming skills in

Python

and working experience with

Go (Golang)

.

Strong software engineering fundamentals, including

Data Structures, Algorithms, APIs, databases, Git, and testing

.

Solid understanding of

Machine Learning and Deep Learning fundamentals

, with experience using PyTorch, TensorFlow, or equivalent.

Hands-on experience with

LLMs, RAG, embeddings, semantic search, and vector databases

.

Good understanding of

system design and distributed-system fundamentals

.

Hands-on experience with

Docker, cloud infrastructure, CI/CD, and production deployment

.

Experience building, deploying, and maintaining

production-grade AI/ML applications

.

Strong problem-solving, debugging, and engineering judgment.

Education

Bachelor’s or Master’s degree in

Computer Science, AI/ML, Data Science, Computer Engineering, Information Technology

, or a related technical discipline.

Good to Have

Experience with

Kubernetes, Terraform, MLflow, Kafka, Redis, PostgreSQL

, or similar production technologies.

Experience with

LLM orchestration and agentic frameworks

such as LangGraph or equivalent.

Exposure to

model serving, inference optimization, GPU workloads, and high-throughput AI systems

.

What We Look For

Engineering mindset:

Ability to build reliable, maintainable, production-quality AI systems.

Ownership:

Ability to take problems from requirements and design through implementation and deployment.