Senior Software Engineer

As a
Senior Software Engineer
, you will design and build scalable backend services and APIs that power modern applications and integrate with Large Language Model (LLM) platforms. You will work closely with architects, product managers, and infrastructure teams to deliver high-performance services, scalable data systems, and reliable integrations with AI technologies.

This role requires strong experience in
backend service development, distributed systems, and cloud-based architectures
, along with exposure to
prompt engineering and LLM-based systems
.

Responsibilities

- Design and develop
scalable APIs and backend services
for high-throughput applications.
- Build
secure, low-latency service endpoints
that integrate with LLM platforms and AI services.
- Develop and maintain
REST or GraphQL APIs
, including clear documentation and service contracts.
- Implement
data storage and caching solutions
using relational databases and distributed caches such as Postgres and Redis.
- Work with
message queues and event-driven architectures
to enable scalable system communication.
- Implement
authentication, authorization, and access control mechanisms
for APIs and services.
- Manage
LLM request batching, rate limits, and performance optimization
for reliable AI integrations.
- Write
well-tested, maintainable code
using strong unit and integration testing practices.
- Contribute to
service observability
, including logging, monitoring, and performance benchmarking.
- Participate in
architecture discussions, design reviews, and peer code reviews
.

Additional Focus: Prompt Engineering & AI Integration

- Design, test, and optimize
prompts and prompt workflows
for LLM and Retrieval-Augmented Generation (RAG) systems.
- Build and maintain
prompt libraries, templates, and prompt chaining strategies
.
- Work with major LLM providers such as
OpenAI, Anthropic, and open-source LLM models
.
- Develop evaluation approaches such as
A/B testing and reproducible test harnesses
to measure prompt performance.
- Implement guardrails to mitigate
hallucinations, prompt injection risks, and safety issues
.
- Optimize prompt usage for
latency, cost efficiency, and response quality
.
- Ensure
privacy-aware handling of sensitive data
, including PHI where required.

Minimum Qualifications

- Bachelor’s degree in Computer Science or related discipline.
- 6+ years of professional software development experience.
- Strong backend experience with
Java or .NET
(or similar server-side languages).
- Experience building
REST or GraphQL APIs
.
- Experience with
relational databases and caching systems
such as
Postgres and Redis
.
- Experience working with
message queues or event-driven systems
.
- Strong understanding of
distributed systems and API performance optimization
.

Preferred Qualifications

- Experience integrating applications with
LLM platforms
such as OpenAI, Anthropic, or open-source models.
- Experience with
RAG pipelines, vector databases, or AI orchestration frameworks
.
- Familiarity with
prompt engineering and evaluation techniques
.
- Experience with
cloud platforms (AWS, Azure, or GCP)
and containerized deployments.
- Experience supporting
production systems at scale
.

Why Join Us:

• Work on cutting-edge real-time data infrastructure that powers critical business use cases.

• Be part of a high-caliber engineering team with a culture of autonomy and excellence.

• Flexible working arrangements with competitive compensation.