MBA Sales Intern

Senior AI Engineer

Code Generation, Agent Architecture & LLM Systems

📍 Mumbai (On-site) | Full-time | 5+ years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are hiring a Senior AI Engineer for a dedicated client engagement focused on building an AI-powered application builder platform - a product where users describe software in plain English and the system generates, previews, and iteratively refines working code.

The mandatory requirement for this role is hands-on production experience shipping LLM-powered systems with agent architectures, with experience in code generation or developer tooling contexts a strong advantage.

The role is product-focused and deeply hands-on. You will own everything between the user's prompt and correct code landing in the project: the agentic loop, code generation pipeline, context management, evaluation suite, and model cost strategy.

You will work alongside the Senior MLOps Engineer who operationalises the infrastructure around your system, and collaborate closely with backend, frontend, and DevOps engineers.

Responsibilities:

Agent Architecture

Design and own the agentic loop for the platform - request interpretation, planning, tool-calling sequence (read file, edit file, run build, search code, install package), and stop conditions.

Make and revisit architectural decisions on single-agent vs. multi-agent designs, including planner/executor splits and dedicated build-repair sub-agents.

Code Generation Pipeline

Own the end-to-end generation flow: task classification, context gathering, planning, targeted edits, verification, and commit.

Implement diff/search-replace-based file editing with fuzzy matching and fallback strategies.

Enforce scope discipline so the agent makes minimal diffs and does not modify code it was not asked to touch.

Self-Repair Loop

Build and tune the automated repair loop that pipes compiler, lint, build, and runtime errors back to the model with retry budgets and model escalation.

This loop is the primary quality lever - the difference between 60-70% and 90%+ build success rates.

Context Management

Build file-relevance retrieval so the agent sees the right files, not the whole codebase: dependency graphs, AST/tree-sitter-based chunking, embeddings, recency signals, and hybrid retrieval.

Implement conversation summarisation and memory for long sessions, and address long-project degradation through codebase summaries and periodic consistency passes.

Own token budgeting and prompt caching strategy.

Prompt Engineering as a Discipline

Own the system prompt and per-task prompt variants (new feature, bug fix, styling change).

Maintain few-shot examples and enforce coding conventions, stack rules, and prohibited behaviours such as no hardcoded secrets and no whole-file rewrites.

Version prompts like code with changelogs and rollback capability.

Evaluation and Quality Measurement

Design and own the evaluation suite: representative test prompts run on every prompt and model change, scored on build success rate, instruction adherence, and output quality including LLM-as-judge and visual/screenshot checks where relevant.

Define regression gates that block quality-degrading changes from shipping.

Treat evals the way engineers treat automated testing: versioned, automated, and tracked over time.

This responsibility is non-negotiable at this level.

Model Strategy and Cost

Design model routing - cheap and fast models for classification and small edits, frontier models for complex generation.

Drive cost optimisation through prompt caching, diff-based edits over full-file rewrites, and tighter context selection.

Track cost per agent run and tokens per task; evaluate new model releases against the eval suite and lead migrations when results justify it.

Safety and Reliability of Agent Behaviour

Defend against prompt injection from user content and fetched web content.

Ensure secrets never appear in generated client code.

Define what the agent's tools may and may not do in collaboration with the platform team.

Contribute to output moderation and abuse-pattern awareness.

Mentorship and Engineering Standards

Run code reviews, define engineering conventions for AI work, and raise the engineering bar across the AI team.

Work closely with the Senior MLOps Engineer on handoff of eval design, prompt configurations, and model routing logic.

Requirements:

Hands-on Production Ownership of LLM-Powered Systems with Agent Architectures (Mandatory)

Must have personally shipped and operated at least one complex production AI system - agentic, multi-step, or code generation - with end-to-end ownership of architecture, evaluation, and cost.

POCs, internal demos, and tutorial-grade work do not qualify.

5+ Years of Professional Software or AI Engineering Experience

With at least 3 years focused on LLM applications, AI engineering, or production AI systems.

Candidates with strong backend backgrounds and a clear, substantive pivot into LLM systems qualify.

Strong Python Proficiency and Service Development

Production-grade Python with FastAPI or equivalent: type hints, async patterns, streaming responses, testing, and packaging.

Not notebook-only.

Depth Across LLM APIs and Agent Systems

Production experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or open-weight models (vLLM, Ollama, Together).

Production experience with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.

Hands-on with tool calling, structured outputs, and multi-step reasoning.

Demonstrated, Systematic Evaluation Practice - Non-Negotiable

Must have built evaluation harnesses that gate production releases, not ad-hoc testing.

Hands-on with at least one of LangSmith, Langfuse, Promptfoo, Ragas, or DeepEval.

Candidates with no systematic answer to evaluation should not be considered at senior level regardless of other strengths.

Cost Discipline for Production AI

Track record of measurable cost optimisation on production AI features.

Able to speak in specifics: cost per request, savings achieved through caching or model routing, context reduction decisions.

AWS Working Knowledge

Hands-on with EC2, S3, IAM, and Docker.

Comfort with CI/CD workflows and deploying AI services.

Awareness of LLM Security Failure Modes

Familiar with prompt injection patterns, understands that system prompt rules alone are insufficient, and has experience with output validation and content safety in production.

Nice to Have

• Experience with AST/tree-sitter tooling, diff-based editing systems, or compiler-adjacent work
• MCP server authoring
• Open-source AI contributions
• Published technical writing on LLM systems
• Multi-modal model experience
• Fine-tuning exposure (LoRA, QLoRA, PEFT)

Job Summary:

We are looking for a talented Senior 3D Designer to join our team. The ideal candidate must demonstrate strong artistic and storytelling ability and possess foundational knowledge of processes, tools, and building blocks of XR – AR/VR, Metaverse. They must also have experience in end-to-end modeling, UV unwrapping, texturing and rendering. The candidate should be proficient in a variety of digital 2D and 3D software programs such as Photoshop, Illustrator, Maya, Blender, etc. This is a great opportunity for someone who is passionate about designing photo-realistic virtual worlds and has 3-5 years of experience as a concept artist or graphic designer.

Responsibilities:

• Create avatar concepts, assets, world-building, materials and texture definition, and environments for photo-realistic virtual worlds
• Use traditional tools and technology to create designs in 2D/3D
• Collaborate with team members and work to a brief by understanding creative briefs, then considering elements such as context, timescales, and creative constraints when solving tasks
• Demonstrate an understanding of technical art production and end-to-end modeling, UV unwrapping, texturing, and rendering
• Develop assets and designs in line with project requirements and timelines
• Ensure all designs are optimized for performance and meet project requirements
• Keep up-to-date with industry trends and emerging technologies

Requirements:

• A portfolio of work demonstrating strong artistic and storytelling ability
• Foundational knowledge of processes, tools, and building blocks of XR – AR/VR, Metaverse
• Excellent sketching abilities for rough conceptualization
• Proficient in a variety of digital 2D and 3D software programs (not limited to Photoshop, Illustrator, Maya, Blender, etc.)
• Ability to work independently and as part of a team
• Strong communication and interpersonal skills
• Ability to manage multiple projects and meet tight deadlines
• 3 - 5 years of experience as a concept artist or graphic designer preferred

Job brief:-

We are looking for an HR Executive to manage our company’s recruiting, learning and development and employee performance programs.

HR Executive responsibilities include creating referral programs, updating HR policies and overseeing our hiring processes. To be successful in this role, you should have an extensive background in Human Resources departments and thorough knowledge of labor legislation.

Ultimately, you will make strategic decisions for our company so that we hire, develop and retain qualified employees.

Responsibilities

• Design compensation and benefits packages
• Implement performance review procedures (e.g. quarterly/annual and 360° evaluations)
• Develop fair HR policies and ensure employees understand and comply with them
• Implement effective sourcing, screening and interviewing techniques
• Assess training needs and coordinate learning and development initiatives for all employees
• Monitor HR department’s budget
• Act as the point of contact regarding labor legislation issues
• Manage employees’ grievances
• Create and run referral bonus programs
• Review current HR technology and recommend more effective software (including HRIS and ATS)
• Measure employee retention and turnover rates
• Oversee daily operations of the HR department

Requirements and skills

• Proven work experience as an HR Executive.
• Familiarity with Human Resources Management Systems and Applicant Tracking Systems
• Experience with full-cycle recruiting
• Good knowledge of labor legislation (particularly employment contracts, employee leaves and insurance)
• Demonstrable leadership abilities
• Solid communication skills

Passionate about automobiles

Proficient knowledge of the auto industry

and updated information about the latest news and production trends in the automobile sector.

Capable of doing good video shoots.

Position - RoR Developer

Responsibilities - 

Candidate should 

• Write clean, maintainable and efficient code
• Design robust, scalable and secure features
• Contribute in all phases of the development lifecycle
• Follow best practices (test-driven development, continuous integration, SCRUM, refactoring and code standards)
• Drive continuous adoption and integration of relevant new technologies into design.

Skills -

• Proven work experience in software development
• Demonstrable knowledge of front-end technologies such as JavaScript, HTML, CSS and JQuery
• Experience developing highly interactive applications
• A firm grasp of object oriented analysis and design
• Passion for writing great, simple, clean, efficient code
• Good knowledge of relational databases
• Working knowledge of NoSQL databases

Experience - 3 years of experience as a Ruby on Rails developer

• We are looking for : Data engineer
• Sprak
• Scala
• Hadoop

• New features developed independently with the ability to document the design after understanding and evaluating the requirements with necessary groundwork on required application components
• Hands-on coding to implement the design for feature completion
• Able to write unit tests that ensures bug free code
• Able to handle the multi-tenant and performance requirements of the new features and applications.
• Integrate the new features with existing modules, deliver ready to use code meeting necessary build requirements and CI/CD requirements.
• Work with other functional groups for product, technology, QA, tech support and deployment team.

‍

The ideal candidate must have the following qualifications.

• BE/B.Tech Degree from a reputed institution with at least 7 years of relevant experience
• Hands-on experience with Core Java, J2EE with a good knowledge of its ecosystem
• Experience with JUnit, JMH like performance tuning test tools preferred
• REST API design and development experience. Usage of Swagger or other API spec tools would be preferred. Working knowledge on Spring Boot is a plus
• Hands-on experience with some of the following application components is a plus: Solr, Kafka, OpenTSDB, Elasticsearch, Janus graph or any graph DB.
• Experience with databases such as MongoDB, MySQL or PostgreSQL required.
• Familiarity with continuous integration and build tools such as Jenkins or CircleCI, Maven, Ant required
• Experience building applications using microservices architecture is highly preferred. Knowledge of Kubernetes, Docker would be ideal
• Working knowledge on public clouds like AWS or Google cloud or Azure is a plus
• Experience building scalable systems
• Strong problem solving skills and ability and interest to solve complex problems
• Interest in machine learning (ML) data science is a plus

Cogoport Story

Do you prefer to get speeding tickets or parking tickets?

Because at Cogoport we are speeding ahead to do something remarkable for the world. We are trying to solve the Trade Knowledge and Execution Gap, which is currently widening and preventing trade to the tune of $3.4 trillion annually. This Gap has enormous economic as well as human impact and disproportionately hits small and medium businesses globally.

The team at Cogoport is working on developing a new category, the Global Trade Platform, that helps companies discover and connect with appropriate trade partners, optimize shipping and logistics options and costs, and improve cash management and cash flow.

Cogoport is currently in hypergrowth mode. We are proud to have been named an Asia-Pacific High-Growth Company by the Financial Times and an Indian Growth Champion by the Economic Times. We are aiming to reach an annualized revenue of $1 billion (7700 Crores INR)  by this summer and are hiring over 500 additional employees. We are currently hiring in Mumbai, Gurgaon, Chennai and Bangalore.

Cogoport Culture: We have two core values at Cogoport—Intrapreneurship and Customer-centricity. If you share these values and are a hard worker who is willing to take risks (and occasionally get a speeding ticket), you can make a huge impact and propel your career in an endless number of directions with Cogoport.

Cogoport Leadership

https://www.linkedin.com/in/purnendushekhar/">https://www.linkedin.com/in/purnendushekhar/
https://www.linkedin.com/in/amitabhshankar/">https://www.linkedin.com/in/amitabhshankar/

Life at Cogoport: It’s rare to be able to join a company that can give you the resources, support and technology you need to break new ground and see your ideas come to life. You’ll be surrounded by some of the smartest engineers and commercial specialists in India and the Asia Pacific Region.

With huge growth and the right entrepreneurial mindset, comes huge opportunities! So, wherever you join us, you’ll be able to dream, deliver better and brighter solutions, and speed ahead with the possibility to propel your career forward in endless directions as our company continues to grow and expand.

For more insights about the company:  https://cogoport.com/about">https://cogoport.com/about

Why Cogoport?

International Trade can be complicated at times and every day brings new challenges and opportunities to learn.  When we simplify international trade, it empowers and affects every human being on the face of this earth. Seven billion people - one common problem.

As a part of the Talent team at Cogoport, you will get an opportunity to be a part of an industry-wide revolution in the world of shipping and logistics by collaborating with other brilliant minds to resolve real world on-ground challenges. You will have a direct impact on the revenue and profitability growth for the organization.

Areas of Impact for you

• Hands-on management with deep-dive into the details of software design, implementation and debugging.
• Guide your teams in developing roadmaps and systems to drive product growth, then identify, plan, and execute projects to support that growth.
• Manage multiple projects across a wide breadth of technologies, coordinate dependencies, and interactions with the internal teams and external partners.
• Collaborate with stakeholders from across functions to keep the development team in sync with all functions and overall business objectives.
• Develop large multi-tenant applications in Rails.
• Understand Rails best practices and religiously introduce those to the codebase.
• Set up, create and manage strong best practices/architecture to ensure reliable, secure, bug-free, and performant software is released on-time.

Desirable Skills and Experience

• Loves coding.
• 2-4 years of experience building scalable & complex products from scratch.
• Demonstrated ability to build complex scalable technology products.
• Should have prior experience of working with ROR, React, PostgreSQL and cloud infra.
• Understanding scaling strategies for high-traffic Rails applications.
• Understanding O-Auth2 or JWT (Json Web Token) authentication mechanisms.
• Experience in using ActiveRecordSerialize, RSpec and active interaction.
• Knowledge about Asynchronous Networking in Ruby; Refactoring ActiveRecord Models; Background Job processing using Redis and Sidekiq; Writing automated Deployment Scripts using Capistrano, Ansible etc.
• Expertise in Data Science and Machine Learning is a pl
• Expertise in Jenkins, Kubernetes, dockers and cloud technology is a plus.

Cogoport is an equal opportunity employer. We are a welcoming place for everyone, and we do our best to make sure all people feel supported and respected at work.