Project Role : Custom Software Engineer
Project Role Description : Lead the effort to design, build and configure applications, acting as the primary point of contact.
Must have skills : Python (Programming Language), React.js
Good to have skills : NA
Minimum 7.5 year(s) of experience is required
Educational Qualification : 15 years full time education

Summary:
As a Senior Python & Generative AI Engineer, your day involves designing, developing, and deploying intelligent software solutions that leverage the power of Generative AI and cloud-native technologies. You engage in iterative development cycles, applying large language model (LLM) integrations, and cloud infrastructure best practices to build scalable, production-grade systems that meet specific business requirements. Collaboration with cross-functional teams — including data scientists, ML engineers, and product stakeholders — along with continuous refinement of AI-driven solutions to enhance performance, reliability, and scalability, are integral parts of your routine, enabling the delivery of robust, efficient, and intelligent software products.

Roles & Responsibilities:

- Expected to be an SME, collaborate and manage the team to perform.
- Responsible for team decisions related to Python development, Generative AI architecture, and cloud infrastructure design.
- Engage with multiple teams and contribute on key decisions involving AI model integration, cloud deployment strategies, and software engineering best practices.
- Provide solutions to problems for their immediate team and across multiple teams, particularly in areas of LLM orchestration, prompt engineering, and cloud-native application development.
- Lead efforts to identify and implement process improvements that enhance team productivity, AI model performance, and overall software quality.
- Mentor junior team members to support their professional growth in Python development, Generative AI tooling, and cloud technologies.
- Coordinate with stakeholders to align software development and AI initiatives with broader business objectives and product roadmaps.




- Drive architectural decisions around the design and deployment of Generative AI pipelines, RAG (Retrieval-Augmented Generation) systems, and agentic workflows.
- Oversee the integration of cloud-based AI/ML services with existing enterprise systems and ensure adherence to security, compliance, and cost-optimization standards.

Professional & Technical Skills:

- Proficiency in Python (Programming Language): with a strong command of writing clean, maintainable, efficient, and production-ready code.
- Generative AI :Hands-on experience working with large language models (LLMs) such as GPT, Claude, Mistral, LLaMA, or similar, including fine-tuning, prompt engineering, and model evaluation.
- Cloud Platforms: Deep expertise in AWS (preferred) services including but not limited to Amazon SageMaker, AWS Bedrock, Lambda, EC2, S3, ECS/EKS, API Gateway, and IAM. Alternatively, strong experience with GCP services such as Vertex AI, Cloud Run, BigQuery, and GKE is acceptable.
- LLM Frameworks & Orchestration : Proficiency in frameworks such as LangChain, LlamaIndex, Haystack, or similar tools for building LLM-powered applications and agentic pipelines.
- Retrieval-Augmented Generation (RAG): Solid, hands-on knowledge and implementation experience with RAG architectures is mandatory. This includes end-to-end design and development of RAG pipelines covering document ingestion, chunking strategies, embedding generation, vector store indexing, semantic search and retrieval, context augmentation, and response generation using LLMs. The candidate must have experience building and optimizing both naive and advanced RAG patterns such as Hybrid RAG, Agentic RAG, Self-RAG, Corrective RAG (CRAG), and Multi-hop RAG. Familiarity with evaluation frameworks for RAG systems such as RAGAS, TruLens, or DeepEval to measure retrieval quality, faithfulness, answer relevance,



and context precision is also expected.
- Vector Databases & Embeddings: Experience with vector stores such as Pinecone, Weaviate, FAISS, ChromaDB, or AWS OpenSearch for building and scaling RAG-based solutions, including management of embedding models such as OpenAI Embeddings, Cohere Embed, or open-source alternatives like Sentence Transformers.
- API Development: Strong experience building and consuming RESTful APIs and microservices using frameworks such as FastAPI, Flask, or Django.
- Infrastructure as Code (IaC): Demonstrated familiarity and hands-on implementation experience with IaC tools, with a strong preference for AWS CloudFormation (CFT) or Terraform. This includes authoring, maintaining, and deploying infrastructure templates for cloud resources such as compute, networking, storage, and AI/ML services, as well as managing infrastructure state, modularizing reusable components, and integrating IaC workflows within CI/CD pipelines to enable automated, repeatable, and auditable infrastructure provisioning.

Additional Information:

- The candidate should have a minimum of 7 years of experience in Python (Programming Language), demonstrating progressive responsibility and depth of expertise.
- The candidate should have a minimum of 2 years of hands-on experience in Generative AI, including working with LLMs, prompt engineering, RAG architectures, or AI agent development.
- The candidate should have a minimum of 5 years of experience in Cloud platforms, with a strong preference for AWS and demonstrated experience deploying and managing production workloads.
- A 15 years full-time education is required.
- Experience working in enterprise-scale environments with cross-functional teams across data science, engineering, and product management is highly desirable.

Strong communication skills are essential, as the role requires regular interaction with both technical and non-technical stakeholders to translate complex AI and cloud concepts into actionable business solutions.
- This position is based at our CODC1A - SEZ location.

15 years full time education

📌 Custom Software Engineer (Coimbatore)
🏢 Accenture
📍 Coimbatore