Job Description

Roles & Responsibility:

Leading the

scalability, integration, and deployment

of our core AI model and associated backend services. Designing, developing, and maintaining

high-performance, reliable Python-based applications

utilising FastAPI and Pydantic. Extensive work with

Postgres RDS

and contributing to the continuous development of our

knowledge graph

. Implementing and optimising solutions for

containerised environments

, leveraging AWS ECS and Fargate. Collaborating with AI/ML specialists to

integrate advanced AI components

(e.g., Graph-based Retrieval-Augmented Generation (RAG), LangChain, Llama Index) and external model inference APIs into the core platform. Defining

build and test scripts

for developed code, working in conjunction with our dedicated DevOps team who manage full CI/CD pipelines. Instantiating necessary simple AWS components via the AWS admin UI or CLI, ensuring smooth operation and integration. Work effectively in a fast-paced, collaborative environment with engineering colleagues and also with product managers, and directly with business subject matter experts upon occasion. Proactively taking a lead technical role in the resolution of outages or technical issues where the cause is application level

Candidate Requirements:

10+ years of software development experience

, with at least

5 years specifically in Python

.

Strong proficiency in Python

and extensive experience with modern frameworks such as

FastAPI

and

Pydantic

. Proven experience with

data engineering principles

and working with relational databases, particularly

Postgres, SQL and ORMs

. Knowledge of graph databases is an advantage but not required. Knowledge of caches like Redis is an advantage but not required. Very strong knowledge of Python internals and technicalities, performance and concurrency E.g. threads vs futures vs processes vs asyncio, generators vs variables, semaphores, queues etc Hands-on experience with

AWS services

, specifically

EC2

/

ECS, Lambda Functions, S3 and RDS

Very strong knowledge of software engineering best practices, including robust testing, code reviews, git branch strategies and management and version control Experience with

containerisation

(e.g., Docker) and CI. Having worked with Github Actions and Kubernetes/EKS is an advantage but not required. Some experience with

Gen

AI concepts

and their Python libraries such as

Retrieval-Augmented Generation (RAG), LangChain, or Llama Index

is desirable but not required (although familiarity with the concepts involved and an interest to get on the leading edge of it is expected). Experience with Python machine learning libraries like NumPy, Pandas, Scikit Learn, Huggingface and the Onnx Runtime are an advantage but not required Likely to have some experience with full stack development or web development, even if not the preferred area to work in. React/NextJS experience a bonus - not expected to be a significant part of the work of the role, but being able to understand the code and work with it when needed independently will make the candidate more efficient Excellent problem-solving skills and a proactive approach to technical challenges. Strong communication skills and capability to provide well structured summaries of problems, solutions, options and investigations

Our Technology Stack:

Backend & AI Integration:

Python (FastAPI, Pydantic), Postgres RDS, Knowledge Graphs

Cloud Platform:

AWS (EC2/ECS, Lambda Functions, S3)

AI/ML:

Graph-based Retrieval-Augmented Generation (Graph RAG), LangChain, OnnxRuntime. Many different LLMs being used for specific purposes as part of a composite system.

Infrastructure:

Containerised architecture on Kubernetes/EKS

Admin tool

: NextJS and ShadCnUI bespoke admin tool

Role Context:

This position offers a significant opportunity to impact a product that is evolving within the legal industry and is a leading use of AI in this sector (a sector that is very well suited to the strengths of Gen AI). The successful candidate will join a dynamic team, addressing complex technical challenges and contributing directly to the expansion of our AI solutions.

The role prioritises strong software engineering fundamentals; candidates are not expected to possess deep DevOps or AWS infrastructure expertise, as these functions are supported by an in-house team, and they are not expected to already possess deep AI technical expertise as long as they are highly motivated to get onto the leading edge of that going forward.

Job Types: Full-time, Permanent

Pay: From ?200,000.00 per month

Application Question(s):

Are you ready to relocate to Ahmedabad?
Work Location: In person